zeroshot's picture
Update README.md
eeabc80
|
raw
history blame
17.4 kB
metadata
tags:
  - mteb
model-index:
  - name: bge-small-en-v1.5-quant
    results:
      - task:
          type: Classification
        dataset:
          type: mteb/amazon_counterfactual
          name: MTEB AmazonCounterfactualClassification (en)
          config: en
          split: test
          revision: e8379541af4e31359cca9fbcf4b00f2671dba205
        metrics:
          - type: accuracy
            value: 74.19402985074626
          - type: ap
            value: 37.562368912364036
          - type: f1
            value: 68.47046663470138
      - task:
          type: Classification
        dataset:
          type: mteb/amazon_polarity
          name: MTEB AmazonPolarityClassification
          config: default
          split: test
          revision: e2d317d38cd51312af73b3d32a06d1a08b442046
        metrics:
          - type: accuracy
            value: 91.89432499999998
          - type: ap
            value: 88.64572979375352
          - type: f1
            value: 91.87171177424113
      - task:
          type: Classification
        dataset:
          type: mteb/amazon_reviews_multi
          name: MTEB AmazonReviewsClassification (en)
          config: en
          split: test
          revision: 1399c76144fd37290681b995c656ef9b2e06e26d
        metrics:
          - type: accuracy
            value: 46.71799999999999
          - type: f1
            value: 46.25791412217894
      - task:
          type: Retrieval
        dataset:
          type: arguana
          name: MTEB ArguAna
          config: default
          split: test
          revision: None
        metrics:
          - type: map_at_1
            value: 34.424
          - type: map_at_10
            value: 49.63
          - type: map_at_100
            value: 50.477000000000004
          - type: map_at_1000
            value: 50.483
          - type: map_at_3
            value: 45.389
          - type: map_at_5
            value: 47.888999999999996
          - type: mrr_at_1
            value: 34.78
          - type: mrr_at_10
            value: 49.793
          - type: mrr_at_100
            value: 50.632999999999996
          - type: mrr_at_1000
            value: 50.638000000000005
          - type: mrr_at_3
            value: 45.531
          - type: mrr_at_5
            value: 48.010000000000005
          - type: ndcg_at_1
            value: 34.424
          - type: ndcg_at_10
            value: 57.774
          - type: ndcg_at_100
            value: 61.248000000000005
          - type: ndcg_at_1000
            value: 61.378
          - type: ndcg_at_3
            value: 49.067
          - type: ndcg_at_5
            value: 53.561
          - type: precision_at_1
            value: 34.424
          - type: precision_at_10
            value: 8.364
          - type: precision_at_100
            value: 0.985
          - type: precision_at_1000
            value: 0.1
          - type: precision_at_3
            value: 19.915
          - type: precision_at_5
            value: 14.124999999999998
          - type: recall_at_1
            value: 34.424
          - type: recall_at_10
            value: 83.64200000000001
          - type: recall_at_100
            value: 98.506
          - type: recall_at_1000
            value: 99.502
          - type: recall_at_3
            value: 59.744
          - type: recall_at_5
            value: 70.626
      - task:
          type: Reranking
        dataset:
          type: mteb/askubuntudupquestions-reranking
          name: MTEB AskUbuntuDupQuestions
          config: default
          split: test
          revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
        metrics:
          - type: map
            value: 62.40334669601722
          - type: mrr
            value: 75.33175042870333
      - task:
          type: STS
        dataset:
          type: mteb/biosses-sts
          name: MTEB BIOSSES
          config: default
          split: test
          revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
        metrics:
          - type: cos_sim_pearson
            value: 88.00433892980047
          - type: cos_sim_spearman
            value: 86.65558896421105
          - type: euclidean_pearson
            value: 85.98927300398377
          - type: euclidean_spearman
            value: 86.0905158476729
          - type: manhattan_pearson
            value: 86.0272425017433
          - type: manhattan_spearman
            value: 85.8929209838941
      - task:
          type: Classification
        dataset:
          type: mteb/banking77
          name: MTEB Banking77Classification
          config: default
          split: test
          revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
        metrics:
          - type: accuracy
            value: 85.1038961038961
          - type: f1
            value: 85.06851570045757
      - task:
          type: Classification
        dataset:
          type: mteb/emotion
          name: MTEB EmotionClassification
          config: default
          split: test
          revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
        metrics:
          - type: accuracy
            value: 46.845
          - type: f1
            value: 41.70045120106269
      - task:
          type: Classification
        dataset:
          type: mteb/imdb
          name: MTEB ImdbClassification
          config: default
          split: test
          revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
        metrics:
          - type: accuracy
            value: 89.3476
          - type: ap
            value: 85.26891728027032
          - type: f1
            value: 89.33488973832894
      - task:
          type: Classification
        dataset:
          type: mteb/mtop_domain
          name: MTEB MTOPDomainClassification (en)
          config: en
          split: test
          revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
        metrics:
          - type: accuracy
            value: 92.67441860465115
          - type: f1
            value: 92.48821366022861
      - task:
          type: Classification
        dataset:
          type: mteb/mtop_intent
          name: MTEB MTOPIntentClassification (en)
          config: en
          split: test
          revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
        metrics:
          - type: accuracy
            value: 74.02872777017784
          - type: f1
            value: 57.28822860484337
      - task:
          type: Classification
        dataset:
          type: mteb/amazon_massive_intent
          name: MTEB MassiveIntentClassification (en)
          config: en
          split: test
          revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
        metrics:
          - type: accuracy
            value: 74.01479488903833
          - type: f1
            value: 71.83716204573571
      - task:
          type: Classification
        dataset:
          type: mteb/amazon_massive_scenario
          name: MTEB MassiveScenarioClassification (en)
          config: en
          split: test
          revision: 7d571f92784cd94a019292a1f45445077d0ef634
        metrics:
          - type: accuracy
            value: 77.95897780766644
          - type: f1
            value: 77.80380046125542
      - task:
          type: STS
        dataset:
          type: mteb/sickr-sts
          name: MTEB SICK-R
          config: default
          split: test
          revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
        metrics:
          - type: cos_sim_pearson
            value: 83.86793477948164
          - type: cos_sim_spearman
            value: 79.43675709317894
          - type: euclidean_pearson
            value: 81.42564463337872
          - type: euclidean_spearman
            value: 79.39138648510273
          - type: manhattan_pearson
            value: 81.31167449689285
          - type: manhattan_spearman
            value: 79.28411420758785
      - task:
          type: STS
        dataset:
          type: mteb/sts12-sts
          name: MTEB STS12
          config: default
          split: test
          revision: a0d554a64d88156834ff5ae9920b964011b16384
        metrics:
          - type: cos_sim_pearson
            value: 84.43490408077298
          - type: cos_sim_spearman
            value: 76.16878340109265
          - type: euclidean_pearson
            value: 80.6016219080782
          - type: euclidean_spearman
            value: 75.67063072565917
          - type: manhattan_pearson
            value: 80.7238920179759
          - type: manhattan_spearman
            value: 75.85631683403953
      - task:
          type: STS
        dataset:
          type: mteb/sts13-sts
          name: MTEB STS13
          config: default
          split: test
          revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
        metrics:
          - type: cos_sim_pearson
            value: 83.03882477767792
          - type: cos_sim_spearman
            value: 84.15171505206217
          - type: euclidean_pearson
            value: 84.11692506470922
          - type: euclidean_spearman
            value: 84.78589046217311
          - type: manhattan_pearson
            value: 83.98651139454486
          - type: manhattan_spearman
            value: 84.64928563751276
      - task:
          type: STS
        dataset:
          type: mteb/sts14-sts
          name: MTEB STS14
          config: default
          split: test
          revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
        metrics:
          - type: cos_sim_pearson
            value: 83.11158600428418
          - type: cos_sim_spearman
            value: 81.48561519933875
          - type: euclidean_pearson
            value: 83.21025907155807
          - type: euclidean_spearman
            value: 81.68699235487654
          - type: manhattan_pearson
            value: 83.16704771658094
          - type: manhattan_spearman
            value: 81.7133110412898
      - task:
          type: STS
        dataset:
          type: mteb/sts15-sts
          name: MTEB STS15
          config: default
          split: test
          revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
        metrics:
          - type: cos_sim_pearson
            value: 87.1514510686502
          - type: cos_sim_spearman
            value: 88.11449450494452
          - type: euclidean_pearson
            value: 87.75854949349939
          - type: euclidean_spearman
            value: 88.4055148221637
          - type: manhattan_pearson
            value: 87.71487828059706
          - type: manhattan_spearman
            value: 88.35301381116254
      - task:
          type: STS
        dataset:
          type: mteb/sts16-sts
          name: MTEB STS16
          config: default
          split: test
          revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
        metrics:
          - type: cos_sim_pearson
            value: 83.36838640113687
          - type: cos_sim_spearman
            value: 84.98776974283366
          - type: euclidean_pearson
            value: 84.0617526427129
          - type: euclidean_spearman
            value: 85.04234805662242
          - type: manhattan_pearson
            value: 83.87433162971784
          - type: manhattan_spearman
            value: 84.87174280390242
      - task:
          type: STS
        dataset:
          type: mteb/sts17-crosslingual-sts
          name: MTEB STS17 (en-en)
          config: en-en
          split: test
          revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
        metrics:
          - type: cos_sim_pearson
            value: 87.72465270691285
          - type: cos_sim_spearman
            value: 87.97672332532184
          - type: euclidean_pearson
            value: 88.78764701492182
          - type: euclidean_spearman
            value: 88.3509718074474
          - type: manhattan_pearson
            value: 88.73024739256215
          - type: manhattan_spearman
            value: 88.24149566970154
      - task:
          type: STS
        dataset:
          type: mteb/sts22-crosslingual-sts
          name: MTEB STS22 (en)
          config: en
          split: test
          revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
        metrics:
          - type: cos_sim_pearson
            value: 64.65195562203238
          - type: cos_sim_spearman
            value: 65.0726777678982
          - type: euclidean_pearson
            value: 65.84698245675273
          - type: euclidean_spearman
            value: 65.13121502162804
          - type: manhattan_pearson
            value: 65.96149904857049
          - type: manhattan_spearman
            value: 65.39983948112955
      - task:
          type: STS
        dataset:
          type: mteb/stsbenchmark-sts
          name: MTEB STSBenchmark
          config: default
          split: test
          revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
        metrics:
          - type: cos_sim_pearson
            value: 85.2642818050049
          - type: cos_sim_spearman
            value: 86.30633382439257
          - type: euclidean_pearson
            value: 86.46510435905633
          - type: euclidean_spearman
            value: 86.62650496446
          - type: manhattan_pearson
            value: 86.2546330637872
          - type: manhattan_spearman
            value: 86.46309860938591
      - task:
          type: PairClassification
        dataset:
          type: mteb/sprintduplicatequestions-pairclassification
          name: MTEB SprintDuplicateQuestions
          config: default
          split: test
          revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
        metrics:
          - type: cos_sim_accuracy
            value: 99.84257425742574
          - type: cos_sim_ap
            value: 96.25445889914926
          - type: cos_sim_f1
            value: 92.03805708562844
          - type: cos_sim_precision
            value: 92.1765295887663
          - type: cos_sim_recall
            value: 91.9
          - type: dot_accuracy
            value: 99.83069306930693
          - type: dot_ap
            value: 96.00517778550396
          - type: dot_f1
            value: 91.27995920448751
          - type: dot_precision
            value: 93.1321540062435
          - type: dot_recall
            value: 89.5
          - type: euclidean_accuracy
            value: 99.84455445544555
          - type: euclidean_ap
            value: 96.14761524546034
          - type: euclidean_f1
            value: 91.97751660705163
          - type: euclidean_precision
            value: 94.04388714733543
          - type: euclidean_recall
            value: 90
          - type: manhattan_accuracy
            value: 99.84158415841584
          - type: manhattan_ap
            value: 96.17014673429341
          - type: manhattan_f1
            value: 91.93790686029043
          - type: manhattan_precision
            value: 92.07622868605817
          - type: manhattan_recall
            value: 91.8
          - type: max_accuracy
            value: 99.84455445544555
          - type: max_ap
            value: 96.25445889914926
          - type: max_f1
            value: 92.03805708562844
      - task:
          type: Classification
        dataset:
          type: mteb/toxic_conversations_50k
          name: MTEB ToxicConversationsClassification
          config: default
          split: test
          revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c
        metrics:
          - type: accuracy
            value: 69.5008
          - type: ap
            value: 13.64158304183089
          - type: f1
            value: 53.50073331072236
      - task:
          type: Classification
        dataset:
          type: mteb/tweet_sentiment_extraction
          name: MTEB TweetSentimentExtractionClassification
          config: default
          split: test
          revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
        metrics:
          - type: accuracy
            value: 60.01980758347483
          - type: f1
            value: 60.35679678249753
      - task:
          type: PairClassification
        dataset:
          type: mteb/twittersemeval2015-pairclassification
          name: MTEB TwitterSemEval2015
          config: default
          split: test
          revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
        metrics:
          - type: cos_sim_accuracy
            value: 85.68874053764081
          - type: cos_sim_ap
            value: 73.26334732095694
          - type: cos_sim_f1
            value: 68.01558376272465
          - type: cos_sim_precision
            value: 64.93880489560834
          - type: cos_sim_recall
            value: 71.39841688654354
          - type: dot_accuracy
            value: 84.71121177802945
          - type: dot_ap
            value: 70.33606362522605
          - type: dot_f1
            value: 65.0887573964497
          - type: dot_precision
            value: 63.50401606425703
          - type: dot_recall
            value: 66.75461741424802
          - type: euclidean_accuracy
            value: 85.80795136198367
          - type: euclidean_ap
            value: 73.43201285001163
          - type: euclidean_f1
            value: 68.33166833166834
          - type: euclidean_precision
            value: 64.86486486486487
          - type: euclidean_recall
            value: 72.18997361477572
          - type: manhattan_accuracy
            value: 85.62317458425225
          - type: manhattan_ap
            value: 73.21212085536185
          - type: manhattan_f1
            value: 68.01681314482232
          - type: manhattan_precision
            value: 65.74735286875153
          - type: manhattan_recall
            value: 70.44854881266491
          - type: max_accuracy
            value: 85.80795136198367
          - type: max_ap
            value: 73.43201285001163
          - type: max_f1
            value: 68.33166833166834
      - task:
          type: PairClassification
        dataset:
          type: mteb/twitterurlcorpus-pairclassification
          name: MTEB TwitterURLCorpus
          config: default
          split: test
          revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
        metrics:
          - type: cos_sim_accuracy
            value: 88.81709162882757
          - type: cos_sim_ap
            value: 85.63540257309367
          - type: cos_sim_f1
            value: 77.9091382258904
          - type: cos_sim_precision
            value: 75.32710280373833
          - type: cos_sim_recall
            value: 80.67446874037573
          - type: dot_accuracy
            value: 88.04478596654636
          - type: dot_ap
            value: 84.16371725220706
          - type: dot_f1
            value: 76.45949643213666
          - type: dot_precision
            value: 73.54719396827655
          - type: dot_recall
            value: 79.61194949183862
          - type: euclidean_accuracy
            value: 88.9296386851399
          - type: euclidean_ap
            value: 85.71894615274715
          - type: euclidean_f1
            value: 78.12952767313823
          - type: euclidean_precision
            value: 73.7688098495212
          - type: euclidean_recall
            value: 83.03818909762857
          - type: manhattan_accuracy
            value: 88.89276982186519
          - type: manhattan_ap
            value: 85.6838514059479
          - type: manhattan_f1
            value: 78.06861875184856
          - type: manhattan_precision
            value: 75.09246088193457
          - type: manhattan_recall
            value: 81.29042192793348
          - type: max_accuracy
            value: 88.9296386851399
          - type: max_ap
            value: 85.71894615274715
          - type: max_f1
            value: 78.12952767313823
license: mit
language:
  - en

license: mit

This is the quantized ONNX variant of the bge-small-en-v1.5 model for embeddings created with DeepSparse Optimum for ONNX export and Neural Magic's Sparsify for One-Shot INT8 quantization.