Hugging Face's logo

sensenova
/
piccolo-base-zh

Feature Extraction
Transformers
PyTorch
bert
mteb
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
5
Jinkin commited on
Commit
e79b872
•
1 Parent(s): 17d3fd3

update base-zh score

Browse files
Files changed (1) hide show
  1. README.md +1056 -1
README.md CHANGED
@@ -1,3 +1,1058 @@
1
  ---
2
- license: mit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
1
  ---
2
+ tags:
3
+ - mteb
4
+ model-index:
5
+ - name: piccolo-base-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: 49.16558217326158
18
+ - type: cos_sim_spearman
19
+ value: 51.4049475858823
20
+ - type: euclidean_pearson
21
+ value: 49.85853741070363
22
+ - type: euclidean_spearman
23
+ value: 51.501428092542234
24
+ - type: manhattan_pearson
25
+ value: 49.746099634926296
26
+ - type: manhattan_spearman
27
+ value: 51.41081804320127
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: 52.385361699031854
39
+ - type: cos_sim_spearman
40
+ value: 52.59114913702212
41
+ - type: euclidean_pearson
42
+ value: 54.994530439418355
43
+ - type: euclidean_spearman
44
+ value: 52.54102886188004
45
+ - type: manhattan_pearson
46
+ value: 54.9503071669608
47
+ - type: manhattan_spearman
48
+ value: 52.51465652540901
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: 40.236
60
+ - type: f1
61
+ value: 39.43040092463147
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: 60.98952187211432
73
+ - type: cos_sim_spearman
74
+ value: 62.68189713123115
75
+ - type: euclidean_pearson
76
+ value: 61.089426749761344
77
+ - type: euclidean_spearman
78
+ value: 62.41743375544581
79
+ - type: manhattan_pearson
80
+ value: 61.14747216341409
81
+ - type: manhattan_spearman
82
+ value: 62.488918956547046
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: 38.36392300667918
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: 35.645927581489175
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: 85.25085782849087
116
+ - type: mrr
117
+ value: 87.77154761904762
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: 86.15357754080844
129
+ - type: mrr
130
+ value: 88.53547619047617
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: 23.683
142
+ - type: map_at_10
143
+ value: 35.522999999999996
144
+ - type: map_at_100
145
+ value: 37.456
146
+ - type: map_at_1000
147
+ value: 37.576
148
+ - type: map_at_3
149
+ value: 31.584
150
+ - type: map_at_5
151
+ value: 33.684999999999995
152
+ - type: mrr_at_1
153
+ value: 36.459
154
+ - type: mrr_at_10
155
+ value: 44.534
156
+ - type: mrr_at_100
157
+ value: 45.6
158
+ - type: mrr_at_1000
159
+ value: 45.647
160
+ - type: mrr_at_3
161
+ value: 42.186
162
+ - type: mrr_at_5
163
+ value: 43.482
164
+ - type: ndcg_at_1
165
+ value: 36.459
166
+ - type: ndcg_at_10
167
+ value: 42.025
168
+ - type: ndcg_at_100
169
+ value: 49.754
170
+ - type: ndcg_at_1000
171
+ value: 51.815999999999995
172
+ - type: ndcg_at_3
173
+ value: 37.056
174
+ - type: ndcg_at_5
175
+ value: 38.962
176
+ - type: precision_at_1
177
+ value: 36.459
178
+ - type: precision_at_10
179
+ value: 9.485000000000001
180
+ - type: precision_at_100
181
+ value: 1.567
182
+ - type: precision_at_1000
183
+ value: 0.183
184
+ - type: precision_at_3
185
+ value: 21.13
186
+ - type: precision_at_5
187
+ value: 15.209
188
+ - type: recall_at_1
189
+ value: 23.683
190
+ - type: recall_at_10
191
+ value: 52.190999999999995
192
+ - type: recall_at_100
193
+ value: 84.491
194
+ - type: recall_at_1000
195
+ value: 98.19600000000001
196
+ - type: recall_at_3
197
+ value: 37.09
198
+ - type: recall_at_5
199
+ value: 43.262
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: 74.20324714371618
211
+ - type: cos_sim_ap
212
+ value: 82.32631646194994
213
+ - type: cos_sim_f1
214
+ value: 76.64052827073876
215
+ - type: cos_sim_precision
216
+ value: 68.58725761772854
217
+ - type: cos_sim_recall
218
+ value: 86.83656768763151
219
+ - type: dot_accuracy
220
+ value: 70.33072760072159
221
+ - type: dot_ap
222
+ value: 77.46972172609794
223
+ - type: dot_f1
224
+ value: 73.6668924804026
225
+ - type: dot_precision
226
+ value: 62.84676354029062
227
+ - type: dot_recall
228
+ value: 88.98760813654431
229
+ - type: euclidean_accuracy
230
+ value: 74.78051713770296
231
+ - type: euclidean_ap
232
+ value: 82.65778389584023
233
+ - type: euclidean_f1
234
+ value: 77.1843623157445
235
+ - type: euclidean_precision
236
+ value: 71.05211406096362
237
+ - type: euclidean_recall
238
+ value: 84.47509936871639
239
+ - type: manhattan_accuracy
240
+ value: 74.76849067949489
241
+ - type: manhattan_ap
242
+ value: 82.55694030572194
243
+ - type: manhattan_f1
244
+ value: 77.1776459569154
245
+ - type: manhattan_precision
246
+ value: 69.5423855963991
247
+ - type: manhattan_recall
248
+ value: 86.69628244096329
249
+ - type: max_accuracy
250
+ value: 74.78051713770296
251
+ - type: max_ap
252
+ value: 82.65778389584023
253
+ - type: max_f1
254
+ value: 77.1843623157445
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: 72.99799999999999
266
+ - type: map_at_10
267
+ value: 81.271
268
+ - type: map_at_100
269
+ value: 81.53399999999999
270
+ - type: map_at_1000
271
+ value: 81.535
272
+ - type: map_at_3
273
+ value: 80.049
274
+ - type: map_at_5
275
+ value: 80.793
276
+ - type: mrr_at_1
277
+ value: 73.13
278
+ - type: mrr_at_10
279
+ value: 81.193
280
+ - type: mrr_at_100
281
+ value: 81.463
282
+ - type: mrr_at_1000
283
+ value: 81.464
284
+ - type: mrr_at_3
285
+ value: 80.067
286
+ - type: mrr_at_5
287
+ value: 80.741
288
+ - type: ndcg_at_1
289
+ value: 73.34
290
+ - type: ndcg_at_10
291
+ value: 84.503
292
+ - type: ndcg_at_100
293
+ value: 85.643
294
+ - type: ndcg_at_1000
295
+ value: 85.693
296
+ - type: ndcg_at_3
297
+ value: 82.135
298
+ - type: ndcg_at_5
299
+ value: 83.401
300
+ - type: precision_at_1
301
+ value: 73.34
302
+ - type: precision_at_10
303
+ value: 9.536
304
+ - type: precision_at_100
305
+ value: 1.004
306
+ - type: precision_at_1000
307
+ value: 0.101
308
+ - type: precision_at_3
309
+ value: 29.54
310
+ - type: precision_at_5
311
+ value: 18.398
312
+ - type: recall_at_1
313
+ value: 72.99799999999999
314
+ - type: recall_at_10
315
+ value: 94.31
316
+ - type: recall_at_100
317
+ value: 99.368
318
+ - type: recall_at_1000
319
+ value: 99.789
320
+ - type: recall_at_3
321
+ value: 87.935
322
+ - type: recall_at_5
323
+ value: 90.991
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: 26.537
335
+ - type: map_at_10
336
+ value: 81.292
337
+ - type: map_at_100
338
+ value: 84.031
339
+ - type: map_at_1000
340
+ value: 84.066
341
+ - type: map_at_3
342
+ value: 56.571000000000005
343
+ - type: map_at_5
344
+ value: 71.082
345
+ - type: mrr_at_1
346
+ value: 91.2
347
+ - type: mrr_at_10
348
+ value: 93.893
349
+ - type: mrr_at_100
350
+ value: 93.955
351
+ - type: mrr_at_1000
352
+ value: 93.95700000000001
353
+ - type: mrr_at_3
354
+ value: 93.61699999999999
355
+ - type: mrr_at_5
356
+ value: 93.767
357
+ - type: ndcg_at_1
358
+ value: 91.2
359
+ - type: ndcg_at_10
360
+ value: 88.255
361
+ - type: ndcg_at_100
362
+ value: 90.813
363
+ - type: ndcg_at_1000
364
+ value: 91.144
365
+ - type: ndcg_at_3
366
+ value: 87.435
367
+ - type: ndcg_at_5
368
+ value: 85.961
369
+ - type: precision_at_1
370
+ value: 91.2
371
+ - type: precision_at_10
372
+ value: 42.14
373
+ - type: precision_at_100
374
+ value: 4.817
375
+ - type: precision_at_1000
376
+ value: 0.48900000000000005
377
+ - type: precision_at_3
378
+ value: 78.467
379
+ - type: precision_at_5
380
+ value: 65.75999999999999
381
+ - type: recall_at_1
382
+ value: 26.537
383
+ - type: recall_at_10
384
+ value: 89.262
385
+ - type: recall_at_100
386
+ value: 97.783
387
+ - type: recall_at_1000
388
+ value: 99.49799999999999
389
+ - type: recall_at_3
390
+ value: 58.573
391
+ - type: recall_at_5
392
+ value: 75.154
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: 48.5
404
+ - type: map_at_10
405
+ value: 57.898
406
+ - type: map_at_100
407
+ value: 58.599000000000004
408
+ - type: map_at_1000
409
+ value: 58.616
410
+ - type: map_at_3
411
+ value: 55.1
412
+ - type: map_at_5
413
+ value: 56.80500000000001
414
+ - type: mrr_at_1
415
+ value: 48.5
416
+ - type: mrr_at_10
417
+ value: 57.898
418
+ - type: mrr_at_100
419
+ value: 58.599000000000004
420
+ - type: mrr_at_1000
421
+ value: 58.616
422
+ - type: mrr_at_3
423
+ value: 55.1
424
+ - type: mrr_at_5
425
+ value: 56.80500000000001
426
+ - type: ndcg_at_1
427
+ value: 48.5
428
+ - type: ndcg_at_10
429
+ value: 62.876
430
+ - type: ndcg_at_100
431
+ value: 66.00200000000001
432
+ - type: ndcg_at_1000
433
+ value: 66.467
434
+ - type: ndcg_at_3
435
+ value: 57.162
436
+ - type: ndcg_at_5
437
+ value: 60.263999999999996
438
+ - type: precision_at_1
439
+ value: 48.5
440
+ - type: precision_at_10
441
+ value: 7.870000000000001
442
+ - type: precision_at_100
443
+ value: 0.927
444
+ - type: precision_at_1000
445
+ value: 0.096
446
+ - type: precision_at_3
447
+ value: 21.032999999999998
448
+ - type: precision_at_5
449
+ value: 14.14
450
+ - type: recall_at_1
451
+ value: 48.5
452
+ - type: recall_at_10
453
+ value: 78.7
454
+ - type: recall_at_100
455
+ value: 92.7
456
+ - type: recall_at_1000
457
+ value: 96.39999999999999
458
+ - type: recall_at_3
459
+ value: 63.1
460
+ - type: recall_at_5
461
+ value: 70.7
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: 44.34782608695652
473
+ - type: f1
474
+ value: 36.401426200836205
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: 84.25891181988743
486
+ - type: ap
487
+ value: 50.54636280166089
488
+ - type: f1
489
+ value: 78.55080202541332
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: 70.02878561337955
501
+ - type: cos_sim_spearman
502
+ value: 75.39509553139982
503
+ - type: euclidean_pearson
504
+ value: 73.92598696939956
505
+ - type: euclidean_spearman
506
+ value: 75.5471147196853
507
+ - type: manhattan_pearson
508
+ value: 73.88049486090739
509
+ - type: manhattan_spearman
510
+ value: 75.51361990583285
511
+ - task:
512
+ type: Retrieval
513
+ dataset:
514
+ type: C-MTEB/MMarcoRetrieval
515
+ name: MTEB MMarcoRetrieval
516
+ config: default
517
+ split: dev
518
+ revision: None
519
+ metrics:
520
+ - type: map_at_1
521
+ value: 64.739
522
+ - type: map_at_10
523
+ value: 74.039
524
+ - type: map_at_100
525
+ value: 74.38
526
+ - type: map_at_1000
527
+ value: 74.39099999999999
528
+ - type: map_at_3
529
+ value: 72.074
530
+ - type: map_at_5
531
+ value: 73.29299999999999
532
+ - type: mrr_at_1
533
+ value: 66.92
534
+ - type: mrr_at_10
535
+ value: 74.636
536
+ - type: mrr_at_100
537
+ value: 74.94
538
+ - type: mrr_at_1000
539
+ value: 74.95
540
+ - type: mrr_at_3
541
+ value: 72.911
542
+ - type: mrr_at_5
543
+ value: 73.981
544
+ - type: ndcg_at_1
545
+ value: 66.92
546
+ - type: ndcg_at_10
547
+ value: 77.924
548
+ - type: ndcg_at_100
549
+ value: 79.471
550
+ - type: ndcg_at_1000
551
+ value: 79.73400000000001
552
+ - type: ndcg_at_3
553
+ value: 74.17200000000001
554
+ - type: ndcg_at_5
555
+ value: 76.236
556
+ - type: precision_at_1
557
+ value: 66.92
558
+ - type: precision_at_10
559
+ value: 9.5
560
+ - type: precision_at_100
561
+ value: 1.027
562
+ - type: precision_at_1000
563
+ value: 0.105
564
+ - type: precision_at_3
565
+ value: 27.989000000000004
566
+ - type: precision_at_5
567
+ value: 17.874000000000002
568
+ - type: recall_at_1
569
+ value: 64.739
570
+ - type: recall_at_10
571
+ value: 89.324
572
+ - type: recall_at_100
573
+ value: 96.342
574
+ - type: recall_at_1000
575
+ value: 98.38900000000001
576
+ - type: recall_at_3
577
+ value: 79.378
578
+ - type: recall_at_5
579
+ value: 84.28099999999999
580
+ - task:
581
+ type: Classification
582
+ dataset:
583
+ type: mteb/amazon_massive_intent
584
+ name: MTEB MassiveIntentClassification (zh-CN)
585
+ config: zh-CN
586
+ split: test
587
+ revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
588
+ metrics:
589
+ - type: accuracy
590
+ value: 68.97108271687962
591
+ - type: f1
592
+ value: 66.8625981386677
593
+ - task:
594
+ type: Classification
595
+ dataset:
596
+ type: mteb/amazon_massive_scenario
597
+ name: MTEB MassiveScenarioClassification (zh-CN)
598
+ config: zh-CN
599
+ split: test
600
+ revision: 7d571f92784cd94a019292a1f45445077d0ef634
601
+ metrics:
602
+ - type: accuracy
603
+ value: 73.32212508406187
604
+ - type: f1
605
+ value: 73.33875034670166
606
+ - task:
607
+ type: Retrieval
608
+ dataset:
609
+ type: C-MTEB/MedicalRetrieval
610
+ name: MTEB MedicalRetrieval
611
+ config: default
612
+ split: dev
613
+ revision: None
614
+ metrics:
615
+ - type: map_at_1
616
+ value: 49.0
617
+ - type: map_at_10
618
+ value: 55.022999999999996
619
+ - type: map_at_100
620
+ value: 55.550999999999995
621
+ - type: map_at_1000
622
+ value: 55.608000000000004
623
+ - type: map_at_3
624
+ value: 53.417
625
+ - type: map_at_5
626
+ value: 54.372
627
+ - type: mrr_at_1
628
+ value: 49.3
629
+ - type: mrr_at_10
630
+ value: 55.176
631
+ - type: mrr_at_100
632
+ value: 55.703
633
+ - type: mrr_at_1000
634
+ value: 55.76
635
+ - type: mrr_at_3
636
+ value: 53.567
637
+ - type: mrr_at_5
638
+ value: 54.522000000000006
639
+ - type: ndcg_at_1
640
+ value: 49.0
641
+ - type: ndcg_at_10
642
+ value: 58.089999999999996
643
+ - type: ndcg_at_100
644
+ value: 60.988
645
+ - type: ndcg_at_1000
646
+ value: 62.580999999999996
647
+ - type: ndcg_at_3
648
+ value: 54.803000000000004
649
+ - type: ndcg_at_5
650
+ value: 56.508
651
+ - type: precision_at_1
652
+ value: 49.0
653
+ - type: precision_at_10
654
+ value: 6.78
655
+ - type: precision_at_100
656
+ value: 0.8210000000000001
657
+ - type: precision_at_1000
658
+ value: 0.095
659
+ - type: precision_at_3
660
+ value: 19.6
661
+ - type: precision_at_5
662
+ value: 12.58
663
+ - type: recall_at_1
664
+ value: 49.0
665
+ - type: recall_at_10
666
+ value: 67.80000000000001
667
+ - type: recall_at_100
668
+ value: 82.1
669
+ - type: recall_at_1000
670
+ value: 94.8
671
+ - type: recall_at_3
672
+ value: 58.8
673
+ - type: recall_at_5
674
+ value: 62.9
675
+ - task:
676
+ type: Reranking
677
+ dataset:
678
+ type: C-MTEB/Mmarco-reranking
679
+ name: MTEB MMarcoReranking
680
+ config: default
681
+ split: dev
682
+ revision: None
683
+ metrics:
684
+ - type: map
685
+ value: 28.87237408060796
686
+ - type: mrr
687
+ value: 27.83015873015873
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: 70.25
699
+ - type: f1
700
+ value: 70.29055400149645
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: 65.56578234975636
712
+ - type: cos_sim_ap
713
+ value: 70.89354058570412
714
+ - type: cos_sim_f1
715
+ value: 71.21024370095002
716
+ - type: cos_sim_precision
717
+ value: 58.48032564450475
718
+ - type: cos_sim_recall
719
+ value: 91.02428722280888
720
+ - type: dot_accuracy
721
+ value: 64.86193827828912
722
+ - type: dot_ap
723
+ value: 70.17697803463875
724
+ - type: dot_f1
725
+ value: 70.68676716917922
726
+ - type: dot_precision
727
+ value: 58.57043719639139
728
+ - type: dot_recall
729
+ value: 89.1235480464625
730
+ - type: euclidean_accuracy
731
+ value: 64.86193827828912
732
+ - type: euclidean_ap
733
+ value: 70.26847152773904
734
+ - type: euclidean_f1
735
+ value: 70.9984152139461
736
+ - type: euclidean_precision
737
+ value: 56.81674064679771
738
+ - type: euclidean_recall
739
+ value: 94.61457233368532
740
+ - type: manhattan_accuracy
741
+ value: 65.40335679480238
742
+ - type: manhattan_ap
743
+ value: 70.22941558736018
744
+ - type: manhattan_f1
745
+ value: 71.09712937475423
746
+ - type: manhattan_precision
747
+ value: 56.64160401002506
748
+ - type: manhattan_recall
749
+ value: 95.45934530095037
750
+ - type: max_accuracy
751
+ value: 65.56578234975636
752
+ - type: max_ap
753
+ value: 70.89354058570412
754
+ - type: max_f1
755
+ value: 71.21024370095002
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: 89.92999999999999
767
+ - type: ap
768
+ value: 87.16059195012956
769
+ - type: f1
770
+ value: 89.90917477839415
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: 27.74161502387672
782
+ - type: cos_sim_spearman
783
+ value: 31.58353529723325
784
+ - type: euclidean_pearson
785
+ value: 32.43729673844635
786
+ - type: euclidean_spearman
787
+ value: 31.59527486602242
788
+ - type: manhattan_pearson
789
+ value: 32.37467059678786
790
+ - type: manhattan_spearman
791
+ value: 31.44408004951894
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: 36.233749845501194
803
+ - type: cos_sim_spearman
804
+ value: 36.47808586229587
805
+ - type: euclidean_pearson
806
+ value: 32.663447466546806
807
+ - type: euclidean_spearman
808
+ value: 34.45830454037139
809
+ - type: manhattan_pearson
810
+ value: 32.80239212096335
811
+ - type: manhattan_spearman
812
+ value: 34.581060433895125
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: None
821
+ metrics:
822
+ - type: cos_sim_pearson
823
+ value: 63.05131937664673
824
+ - type: cos_sim_spearman
825
+ value: 66.51353746725948
826
+ - type: euclidean_pearson
827
+ value: 61.24016998745561
828
+ - type: euclidean_spearman
829
+ value: 66.07115266049276
830
+ - type: manhattan_pearson
831
+ value: 64.55660243659054
832
+ - type: manhattan_spearman
833
+ value: 66.80282149562386
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: 70.45533692882996
845
+ - type: cos_sim_spearman
846
+ value: 70.6045637565602
847
+ - type: euclidean_pearson
848
+ value: 72.75588977483554
849
+ - type: euclidean_spearman
850
+ value: 73.36630581886473
851
+ - type: manhattan_pearson
852
+ value: 72.72517409326954
853
+ - type: manhattan_spearman
854
+ value: 73.35358940437355
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: 66.45779474032288
866
+ - type: mrr
867
+ value: 76.0782192023729
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: 26.458
879
+ - type: map_at_10
880
+ value: 74.355
881
+ - type: map_at_100
882
+ value: 78.158
883
+ - type: map_at_1000
884
+ value: 78.233
885
+ - type: map_at_3
886
+ value: 52.2
887
+ - type: map_at_5
888
+ value: 64.14
889
+ - type: mrr_at_1
890
+ value: 88.37
891
+ - type: mrr_at_10
892
+ value: 91.117
893
+ - type: mrr_at_100
894
+ value: 91.231
895
+ - type: mrr_at_1000
896
+ value: 91.23599999999999
897
+ - type: mrr_at_3
898
+ value: 90.645
899
+ - type: mrr_at_5
900
+ value: 90.948
901
+ - type: ndcg_at_1
902
+ value: 88.37
903
+ - type: ndcg_at_10
904
+ value: 82.384
905
+ - type: ndcg_at_100
906
+ value: 86.431
907
+ - type: ndcg_at_1000
908
+ value: 87.163
909
+ - type: ndcg_at_3
910
+ value: 83.993
911
+ - type: ndcg_at_5
912
+ value: 82.411
913
+ - type: precision_at_1
914
+ value: 88.37
915
+ - type: precision_at_10
916
+ value: 41.131
917
+ - type: precision_at_100
918
+ value: 4.9799999999999995
919
+ - type: precision_at_1000
920
+ value: 0.515
921
+ - type: precision_at_3
922
+ value: 73.651
923
+ - type: precision_at_5
924
+ value: 61.634
925
+ - type: recall_at_1
926
+ value: 26.458
927
+ - type: recall_at_10
928
+ value: 81.3
929
+ - type: recall_at_100
930
+ value: 94.342
931
+ - type: recall_at_1000
932
+ value: 98.103
933
+ - type: recall_at_3
934
+ value: 54.020999999999994
935
+ - type: recall_at_5
936
+ value: 67.781
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: 46.814
948
+ - type: f1
949
+ value: 45.580027683507666
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: 61.43613064816144
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: 53.01838461793776
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: 59.3
983
+ - type: map_at_10
984
+ value: 69.158
985
+ - type: map_at_100
986
+ value: 69.60300000000001
987
+ - type: map_at_1000
988
+ value: 69.611
989
+ - type: map_at_3
990
+ value: 67.467
991
+ - type: map_at_5
992
+ value: 68.432
993
+ - type: mrr_at_1
994
+ value: 59.199999999999996
995
+ - type: mrr_at_10
996
+ value: 69.108
997
+ - type: mrr_at_100
998
+ value: 69.553
999
+ - type: mrr_at_1000
1000
+ value: 69.56099999999999
1001
+ - type: mrr_at_3
1002
+ value: 67.417
1003
+ - type: mrr_at_5
1004
+ value: 68.382
1005
+ - type: ndcg_at_1
1006
+ value: 59.3
1007
+ - type: ndcg_at_10
1008
+ value: 73.54
1009
+ - type: ndcg_at_100
1010
+ value: 75.652
1011
+ - type: ndcg_at_1000
1012
+ value: 75.868
1013
+ - type: ndcg_at_3
1014
+ value: 70.074
1015
+ - type: ndcg_at_5
1016
+ value: 71.808
1017
+ - type: precision_at_1
1018
+ value: 59.3
1019
+ - type: precision_at_10
1020
+ value: 8.709999999999999
1021
+ - type: precision_at_100
1022
+ value: 0.9690000000000001
1023
+ - type: precision_at_1000
1024
+ value: 0.099
1025
+ - type: precision_at_3
1026
+ value: 25.867
1027
+ - type: precision_at_5
1028
+ value: 16.36
1029
+ - type: recall_at_1
1030
+ value: 59.3
1031
+ - type: recall_at_10
1032
+ value: 87.1
1033
+ - type: recall_at_100
1034
+ value: 96.89999999999999
1035
+ - type: recall_at_1000
1036
+ value: 98.6
1037
+ - type: recall_at_3
1038
+ value: 77.60000000000001
1039
+ - type: recall_at_5
1040
+ value: 81.8
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: 84.69999999999999
1052
+ - type: ap
1053
+ value: 66.65020528563207
1054
+ - type: f1
1055
+ value: 83.00542769081453
1056
  ---
1057
+
1058
+ ## piccolo-base-zh