nomic / README.md
Severian's picture
Update README.md
8cc18c5 verified
---
library_name: sentence-transformers
pipeline_tag: feature-extraction
tags:
- feature-extraction
- sentence-similarity
- mteb
- transformers
- transformers.js
model-index:
- name: epoch_0_model
results:
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en)
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 76.8507462686567
- type: ap
value: 40.592189159090495
- type: f1
value: 71.01634655512476
- task:
type: Classification
dataset:
type: mteb/amazon_polarity
name: MTEB AmazonPolarityClassification
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 91.51892500000001
- type: ap
value: 88.50346762975335
- type: f1
value: 91.50342077459624
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (en)
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 47.364
- type: f1
value: 46.72708080922794
- task:
type: Retrieval
dataset:
type: arguana
name: MTEB ArguAna
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 25.178
- type: map_at_10
value: 40.244
- type: map_at_100
value: 41.321999999999996
- type: map_at_1000
value: 41.331
- type: map_at_3
value: 35.016999999999996
- type: map_at_5
value: 37.99
- type: mrr_at_1
value: 25.605
- type: mrr_at_10
value: 40.422000000000004
- type: mrr_at_100
value: 41.507
- type: mrr_at_1000
value: 41.516
- type: mrr_at_3
value: 35.23
- type: mrr_at_5
value: 38.15
- type: ndcg_at_1
value: 25.178
- type: ndcg_at_10
value: 49.258
- type: ndcg_at_100
value: 53.776
- type: ndcg_at_1000
value: 53.995000000000005
- type: ndcg_at_3
value: 38.429
- type: ndcg_at_5
value: 43.803
- type: precision_at_1
value: 25.178
- type: precision_at_10
value: 7.831
- type: precision_at_100
value: 0.979
- type: precision_at_1000
value: 0.1
- type: precision_at_3
value: 16.121
- type: precision_at_5
value: 12.29
- type: recall_at_1
value: 25.178
- type: recall_at_10
value: 78.307
- type: recall_at_100
value: 97.866
- type: recall_at_1000
value: 99.57300000000001
- type: recall_at_3
value: 48.364000000000004
- type: recall_at_5
value: 61.451
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-p2p
name: MTEB ArxivClusteringP2P
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure
value: 45.93034494751465
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-s2s
name: MTEB ArxivClusteringS2S
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure
value: 36.64579480054327
- task:
type: Reranking
dataset:
type: mteb/askubuntudupquestions-reranking
name: MTEB AskUbuntuDupQuestions
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 60.601310529222054
- type: mrr
value: 75.04484896451656
- task:
type: STS
dataset:
type: mteb/biosses-sts
name: MTEB BIOSSES
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 88.57797718095814
- type: cos_sim_spearman
value: 86.47064499110101
- type: euclidean_pearson
value: 87.4559602783142
- type: euclidean_spearman
value: 86.47064499110101
- type: manhattan_pearson
value: 87.7232764230245
- type: manhattan_spearman
value: 86.91222131777742
- task:
type: Classification
dataset:
type: mteb/banking77
name: MTEB Banking77Classification
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 84.5422077922078
- type: f1
value: 84.47657456950589
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-p2p
name: MTEB BiorxivClusteringP2P
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure
value: 38.48953561974464
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-s2s
name: MTEB BiorxivClusteringS2S
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure
value: 32.75995857510105
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackAndroidRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 30.008000000000003
- type: map_at_10
value: 39.51
- type: map_at_100
value: 40.841
- type: map_at_1000
value: 40.973
- type: map_at_3
value: 36.248999999999995
- type: map_at_5
value: 38.096999999999994
- type: mrr_at_1
value: 36.481
- type: mrr_at_10
value: 44.818000000000005
- type: mrr_at_100
value: 45.64
- type: mrr_at_1000
value: 45.687
- type: mrr_at_3
value: 42.036
- type: mrr_at_5
value: 43.782
- type: ndcg_at_1
value: 36.481
- type: ndcg_at_10
value: 45.152
- type: ndcg_at_100
value: 50.449
- type: ndcg_at_1000
value: 52.76499999999999
- type: ndcg_at_3
value: 40.161
- type: ndcg_at_5
value: 42.577999999999996
- type: precision_at_1
value: 36.481
- type: precision_at_10
value: 8.369
- type: precision_at_100
value: 1.373
- type: precision_at_1000
value: 0.186
- type: precision_at_3
value: 18.693
- type: precision_at_5
value: 13.533999999999999
- type: recall_at_1
value: 30.008000000000003
- type: recall_at_10
value: 56.108999999999995
- type: recall_at_100
value: 78.55499999999999
- type: recall_at_1000
value: 93.659
- type: recall_at_3
value: 41.754999999999995
- type: recall_at_5
value: 48.296
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackEnglishRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 30.262
- type: map_at_10
value: 40.139
- type: map_at_100
value: 41.394
- type: map_at_1000
value: 41.526
- type: map_at_3
value: 37.155
- type: map_at_5
value: 38.785
- type: mrr_at_1
value: 38.153
- type: mrr_at_10
value: 46.369
- type: mrr_at_100
value: 47.072
- type: mrr_at_1000
value: 47.111999999999995
- type: mrr_at_3
value: 44.268
- type: mrr_at_5
value: 45.389
- type: ndcg_at_1
value: 38.153
- type: ndcg_at_10
value: 45.925
- type: ndcg_at_100
value: 50.394000000000005
- type: ndcg_at_1000
value: 52.37500000000001
- type: ndcg_at_3
value: 41.754000000000005
- type: ndcg_at_5
value: 43.574
- type: precision_at_1
value: 38.153
- type: precision_at_10
value: 8.796
- type: precision_at_100
value: 1.432
- type: precision_at_1000
value: 0.189
- type: precision_at_3
value: 20.318
- type: precision_at_5
value: 14.395
- type: recall_at_1
value: 30.262
- type: recall_at_10
value: 55.72200000000001
- type: recall_at_100
value: 74.97500000000001
- type: recall_at_1000
value: 87.342
- type: recall_at_3
value: 43.129
- type: recall_at_5
value: 48.336
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGamingRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 39.951
- type: map_at_10
value: 51.248000000000005
- type: map_at_100
value: 52.188
- type: map_at_1000
value: 52.247
- type: map_at_3
value: 48.211
- type: map_at_5
value: 49.797000000000004
- type: mrr_at_1
value: 45.329
- type: mrr_at_10
value: 54.749
- type: mrr_at_100
value: 55.367999999999995
- type: mrr_at_1000
value: 55.400000000000006
- type: mrr_at_3
value: 52.382
- type: mrr_at_5
value: 53.649
- type: ndcg_at_1
value: 45.329
- type: ndcg_at_10
value: 56.847
- type: ndcg_at_100
value: 60.738
- type: ndcg_at_1000
value: 61.976
- type: ndcg_at_3
value: 51.59
- type: ndcg_at_5
value: 53.915
- type: precision_at_1
value: 45.329
- type: precision_at_10
value: 8.959
- type: precision_at_100
value: 1.187
- type: precision_at_1000
value: 0.134
- type: precision_at_3
value: 22.612
- type: precision_at_5
value: 15.273
- type: recall_at_1
value: 39.951
- type: recall_at_10
value: 70.053
- type: recall_at_100
value: 86.996
- type: recall_at_1000
value: 95.707
- type: recall_at_3
value: 56.032000000000004
- type: recall_at_5
value: 61.629999999999995
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGisRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 25.566
- type: map_at_10
value: 33.207
- type: map_at_100
value: 34.166000000000004
- type: map_at_1000
value: 34.245
- type: map_at_3
value: 30.94
- type: map_at_5
value: 32.01
- type: mrr_at_1
value: 27.345000000000002
- type: mrr_at_10
value: 35.193000000000005
- type: mrr_at_100
value: 35.965
- type: mrr_at_1000
value: 36.028999999999996
- type: mrr_at_3
value: 32.806000000000004
- type: mrr_at_5
value: 34.021
- type: ndcg_at_1
value: 27.345000000000002
- type: ndcg_at_10
value: 37.891999999999996
- type: ndcg_at_100
value: 42.664
- type: ndcg_at_1000
value: 44.757000000000005
- type: ndcg_at_3
value: 33.123000000000005
- type: ndcg_at_5
value: 35.035
- type: precision_at_1
value: 27.345000000000002
- type: precision_at_10
value: 5.763
- type: precision_at_100
value: 0.859
- type: precision_at_1000
value: 0.108
- type: precision_at_3
value: 13.71
- type: precision_at_5
value: 9.401
- type: recall_at_1
value: 25.566
- type: recall_at_10
value: 50.563
- type: recall_at_100
value: 72.86399999999999
- type: recall_at_1000
value: 88.68599999999999
- type: recall_at_3
value: 37.43
- type: recall_at_5
value: 41.894999999999996
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackMathematicaRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 16.663
- type: map_at_10
value: 23.552
- type: map_at_100
value: 24.538
- type: map_at_1000
value: 24.661
- type: map_at_3
value: 21.085
- type: map_at_5
value: 22.391
- type: mrr_at_1
value: 20.025000000000002
- type: mrr_at_10
value: 27.643
- type: mrr_at_100
value: 28.499999999999996
- type: mrr_at_1000
value: 28.582
- type: mrr_at_3
value: 25.083
- type: mrr_at_5
value: 26.544
- type: ndcg_at_1
value: 20.025000000000002
- type: ndcg_at_10
value: 28.272000000000002
- type: ndcg_at_100
value: 33.353
- type: ndcg_at_1000
value: 36.454
- type: ndcg_at_3
value: 23.579
- type: ndcg_at_5
value: 25.685000000000002
- type: precision_at_1
value: 20.025000000000002
- type: precision_at_10
value: 5.187
- type: precision_at_100
value: 0.897
- type: precision_at_1000
value: 0.13
- type: precision_at_3
value: 10.987
- type: precision_at_5
value: 8.06
- type: recall_at_1
value: 16.663
- type: recall_at_10
value: 38.808
- type: recall_at_100
value: 61.305
- type: recall_at_1000
value: 83.571
- type: recall_at_3
value: 25.907999999999998
- type: recall_at_5
value: 31.214
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackPhysicsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 27.695999999999998
- type: map_at_10
value: 37.018
- type: map_at_100
value: 38.263000000000005
- type: map_at_1000
value: 38.371
- type: map_at_3
value: 34.226
- type: map_at_5
value: 35.809999999999995
- type: mrr_at_1
value: 32.916000000000004
- type: mrr_at_10
value: 42.067
- type: mrr_at_100
value: 42.925000000000004
- type: mrr_at_1000
value: 42.978
- type: mrr_at_3
value: 39.637
- type: mrr_at_5
value: 41.134
- type: ndcg_at_1
value: 32.916000000000004
- type: ndcg_at_10
value: 42.539
- type: ndcg_at_100
value: 47.873
- type: ndcg_at_1000
value: 50.08200000000001
- type: ndcg_at_3
value: 37.852999999999994
- type: ndcg_at_5
value: 40.201
- type: precision_at_1
value: 32.916000000000004
- type: precision_at_10
value: 7.5840000000000005
- type: precision_at_100
value: 1.199
- type: precision_at_1000
value: 0.155
- type: precision_at_3
value: 17.485
- type: precision_at_5
value: 12.512
- type: recall_at_1
value: 27.695999999999998
- type: recall_at_10
value: 53.638
- type: recall_at_100
value: 76.116
- type: recall_at_1000
value: 91.069
- type: recall_at_3
value: 41.13
- type: recall_at_5
value: 46.872
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackProgrammersRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 24.108
- type: map_at_10
value: 33.372
- type: map_at_100
value: 34.656
- type: map_at_1000
value: 34.768
- type: map_at_3
value: 30.830999999999996
- type: map_at_5
value: 32.204
- type: mrr_at_1
value: 29.110000000000003
- type: mrr_at_10
value: 37.979
- type: mrr_at_100
value: 38.933
- type: mrr_at_1000
value: 38.988
- type: mrr_at_3
value: 35.731
- type: mrr_at_5
value: 36.963
- type: ndcg_at_1
value: 29.110000000000003
- type: ndcg_at_10
value: 38.635000000000005
- type: ndcg_at_100
value: 44.324999999999996
- type: ndcg_at_1000
value: 46.747
- type: ndcg_at_3
value: 34.37
- type: ndcg_at_5
value: 36.228
- type: precision_at_1
value: 29.110000000000003
- type: precision_at_10
value: 6.963
- type: precision_at_100
value: 1.146
- type: precision_at_1000
value: 0.152
- type: precision_at_3
value: 16.400000000000002
- type: precision_at_5
value: 11.552999999999999
- type: recall_at_1
value: 24.108
- type: recall_at_10
value: 49.597
- type: recall_at_100
value: 73.88900000000001
- type: recall_at_1000
value: 90.62400000000001
- type: recall_at_3
value: 37.662
- type: recall_at_5
value: 42.565
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 25.00791666666667
- type: map_at_10
value: 33.287749999999996
- type: map_at_100
value: 34.41141666666667
- type: map_at_1000
value: 34.52583333333333
- type: map_at_3
value: 30.734416666666668
- type: map_at_5
value: 32.137166666666666
- type: mrr_at_1
value: 29.305666666666664
- type: mrr_at_10
value: 37.22966666666666
- type: mrr_at_100
value: 38.066583333333334
- type: mrr_at_1000
value: 38.12616666666667
- type: mrr_at_3
value: 34.92275
- type: mrr_at_5
value: 36.23333333333334
- type: ndcg_at_1
value: 29.305666666666664
- type: ndcg_at_10
value: 38.25533333333333
- type: ndcg_at_100
value: 43.25266666666666
- type: ndcg_at_1000
value: 45.63583333333334
- type: ndcg_at_3
value: 33.777166666666666
- type: ndcg_at_5
value: 35.85
- type: precision_at_1
value: 29.305666666666664
- type: precision_at_10
value: 6.596416666666667
- type: precision_at_100
value: 1.0784166666666668
- type: precision_at_1000
value: 0.14666666666666664
- type: precision_at_3
value: 15.31075
- type: precision_at_5
value: 10.830916666666667
- type: recall_at_1
value: 25.00791666666667
- type: recall_at_10
value: 49.10933333333333
- type: recall_at_100
value: 71.09216666666667
- type: recall_at_1000
value: 87.77725000000001
- type: recall_at_3
value: 36.660916666666665
- type: recall_at_5
value: 41.94149999999999
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackStatsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 23.521
- type: map_at_10
value: 30.043
- type: map_at_100
value: 30.936000000000003
- type: map_at_1000
value: 31.022
- type: map_at_3
value: 27.926000000000002
- type: map_at_5
value: 29.076999999999998
- type: mrr_at_1
value: 26.227
- type: mrr_at_10
value: 32.822
- type: mrr_at_100
value: 33.61
- type: mrr_at_1000
value: 33.672000000000004
- type: mrr_at_3
value: 30.776999999999997
- type: mrr_at_5
value: 31.866
- type: ndcg_at_1
value: 26.227
- type: ndcg_at_10
value: 34.041
- type: ndcg_at_100
value: 38.394
- type: ndcg_at_1000
value: 40.732
- type: ndcg_at_3
value: 30.037999999999997
- type: ndcg_at_5
value: 31.845000000000002
- type: precision_at_1
value: 26.227
- type: precision_at_10
value: 5.244999999999999
- type: precision_at_100
value: 0.808
- type: precision_at_1000
value: 0.107
- type: precision_at_3
value: 12.679000000000002
- type: precision_at_5
value: 8.773
- type: recall_at_1
value: 23.521
- type: recall_at_10
value: 43.633
- type: recall_at_100
value: 63.126000000000005
- type: recall_at_1000
value: 80.765
- type: recall_at_3
value: 32.614
- type: recall_at_5
value: 37.15
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack