zeroshot's picture
Update README.md
a741025
|
raw
history blame
15.6 kB
metadata
tags:
  - mteb
  - sparse sparsity quantized onnx embeddings int8
model-index:
  - name: bge-small-en-v1.5-sparse
    results:
      - task:
          type: Classification
        dataset:
          type: mteb/amazon_counterfactual
          name: MTEB AmazonCounterfactualClassification (en)
          config: en
          split: test
          revision: e8379541af4e31359cca9fbcf4b00f2671dba205
        metrics:
          - type: accuracy
            value: 70.71641791044776
          - type: ap
            value: 32.850850647310004
          - type: f1
            value: 64.48101916414805
      - task:
          type: Classification
        dataset:
          type: mteb/amazon_polarity
          name: MTEB AmazonPolarityClassification
          config: default
          split: test
          revision: e2d317d38cd51312af73b3d32a06d1a08b442046
        metrics:
          - type: accuracy
            value: 83.33962500000001
          - type: ap
            value: 78.28706349240106
          - type: f1
            value: 83.27426715603062
      - task:
          type: Classification
        dataset:
          type: mteb/amazon_reviews_multi
          name: MTEB AmazonReviewsClassification (en)
          config: en
          split: test
          revision: 1399c76144fd37290681b995c656ef9b2e06e26d
        metrics:
          - type: accuracy
            value: 40.988
          - type: f1
            value: 40.776679545648506
      - task:
          type: STS
        dataset:
          type: mteb/biosses-sts
          name: MTEB BIOSSES
          config: default
          split: test
          revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
        metrics:
          - type: cos_sim_pearson
            value: 79.64892774481326
          - type: cos_sim_spearman
            value: 78.953003817029
          - type: euclidean_pearson
            value: 78.92456838230683
          - type: euclidean_spearman
            value: 78.56504316985354
          - type: manhattan_pearson
            value: 79.21436359014227
          - type: manhattan_spearman
            value: 78.66263575501259
      - task:
          type: Classification
        dataset:
          type: mteb/banking77
          name: MTEB Banking77Classification
          config: default
          split: test
          revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
        metrics:
          - type: accuracy
            value: 81.25
          - type: f1
            value: 81.20841448916138
      - task:
          type: Classification
        dataset:
          type: mteb/emotion
          name: MTEB EmotionClassification
          config: default
          split: test
          revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
        metrics:
          - type: accuracy
            value: 41.665
          - type: f1
            value: 37.601137843331244
      - task:
          type: Classification
        dataset:
          type: mteb/imdb
          name: MTEB ImdbClassification
          config: default
          split: test
          revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
        metrics:
          - type: accuracy
            value: 74.8052
          - type: ap
            value: 68.92588517572685
          - type: f1
            value: 74.66801685854456
      - task:
          type: Classification
        dataset:
          type: mteb/mtop_domain
          name: MTEB MTOPDomainClassification (en)
          config: en
          split: test
          revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
        metrics:
          - type: accuracy
            value: 91.2220702234382
          - type: f1
            value: 90.81687856852439
      - task:
          type: Classification
        dataset:
          type: mteb/mtop_intent
          name: MTEB MTOPIntentClassification (en)
          config: en
          split: test
          revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
        metrics:
          - type: accuracy
            value: 69.39124487004105
          - type: f1
            value: 51.8350043424968
      - task:
          type: Classification
        dataset:
          type: mteb/amazon_massive_intent
          name: MTEB MassiveIntentClassification (en)
          config: en
          split: test
          revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
        metrics:
          - type: accuracy
            value: 69.80497646267652
          - type: f1
            value: 67.34213899244814
      - task:
          type: Classification
        dataset:
          type: mteb/amazon_massive_scenario
          name: MTEB MassiveScenarioClassification (en)
          config: en
          split: test
          revision: 7d571f92784cd94a019292a1f45445077d0ef634
        metrics:
          - type: accuracy
            value: 74.54270342972428
          - type: f1
            value: 74.02802500235784
      - task:
          type: STS
        dataset:
          type: mteb/sickr-sts
          name: MTEB SICK-R
          config: default
          split: test
          revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
        metrics:
          - type: cos_sim_pearson
            value: 80.89215288990194
          - type: cos_sim_spearman
            value: 74.386413188675
          - type: euclidean_pearson
            value: 78.83679563989534
          - type: euclidean_spearman
            value: 74.29328198771996
          - type: manhattan_pearson
            value: 78.77968796707641
          - type: manhattan_spearman
            value: 74.20887429784696
      - task:
          type: STS
        dataset:
          type: mteb/sts12-sts
          name: MTEB STS12
          config: default
          split: test
          revision: a0d554a64d88156834ff5ae9920b964011b16384
        metrics:
          - type: cos_sim_pearson
            value: 78.31858821914498
          - type: cos_sim_spearman
            value: 72.2217008523832
          - type: euclidean_pearson
            value: 75.38901061978429
          - type: euclidean_spearman
            value: 71.81255767675184
          - type: manhattan_pearson
            value: 75.49472202181288
          - type: manhattan_spearman
            value: 71.96322588726144
      - task:
          type: STS
        dataset:
          type: mteb/sts13-sts
          name: MTEB STS13
          config: default
          split: test
          revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
        metrics:
          - type: cos_sim_pearson
            value: 79.48334648997455
          - type: cos_sim_spearman
            value: 80.99654029572798
          - type: euclidean_pearson
            value: 80.46546523970035
          - type: euclidean_spearman
            value: 80.90646216980744
          - type: manhattan_pearson
            value: 80.35474057857608
          - type: manhattan_spearman
            value: 80.8141299909659
      - task:
          type: STS
        dataset:
          type: mteb/sts14-sts
          name: MTEB STS14
          config: default
          split: test
          revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
        metrics:
          - type: cos_sim_pearson
            value: 79.73826970784727
          - type: cos_sim_spearman
            value: 76.9926870133034
          - type: euclidean_pearson
            value: 79.6386542120984
          - type: euclidean_spearman
            value: 77.05041986942253
          - type: manhattan_pearson
            value: 79.61799508502459
          - type: manhattan_spearman
            value: 77.07169617647067
      - task:
          type: STS
        dataset:
          type: mteb/sts15-sts
          name: MTEB STS15
          config: default
          split: test
          revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
        metrics:
          - type: cos_sim_pearson
            value: 83.93999019426069
          - type: cos_sim_spearman
            value: 85.21166521594695
          - type: euclidean_pearson
            value: 84.97207676326357
          - type: euclidean_spearman
            value: 85.40726578482739
          - type: manhattan_pearson
            value: 85.0386693192183
          - type: manhattan_spearman
            value: 85.49230945586409
      - task:
          type: STS
        dataset:
          type: mteb/sts16-sts
          name: MTEB STS16
          config: default
          split: test
          revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
        metrics:
          - type: cos_sim_pearson
            value: 80.8133974034008
          - type: cos_sim_spearman
            value: 82.82919022688844
          - type: euclidean_pearson
            value: 81.92587923760179
          - type: euclidean_spearman
            value: 82.86629450518863
          - type: manhattan_pearson
            value: 81.98232365999253
          - type: manhattan_spearman
            value: 82.94313939920296
      - 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: 86.12872422642363
          - type: cos_sim_spearman
            value: 87.77672179979807
          - type: euclidean_pearson
            value: 87.76172961705947
          - type: euclidean_spearman
            value: 87.9891393339215
          - type: manhattan_pearson
            value: 87.78863663568221
          - type: manhattan_spearman
            value: 88.08297053203866
      - 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: 58.82824030232733
          - type: cos_sim_spearman
            value: 64.17079382633538
          - type: euclidean_pearson
            value: 61.31505225602925
          - type: euclidean_spearman
            value: 64.05080034530694
          - type: manhattan_pearson
            value: 61.77095758943306
          - type: manhattan_spearman
            value: 64.14475973774933
      - task:
          type: STS
        dataset:
          type: mteb/stsbenchmark-sts
          name: MTEB STSBenchmark
          config: default
          split: test
          revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
        metrics:
          - type: cos_sim_pearson
            value: 81.39239803497064
          - type: cos_sim_spearman
            value: 81.76637354520439
          - type: euclidean_pearson
            value: 82.98008209033587
          - type: euclidean_spearman
            value: 82.18662536188657
          - type: manhattan_pearson
            value: 82.9630328314908
          - type: manhattan_spearman
            value: 82.13726553603003
      - task:
          type: PairClassification
        dataset:
          type: mteb/sprintduplicatequestions-pairclassification
          name: MTEB SprintDuplicateQuestions
          config: default
          split: test
          revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
        metrics:
          - type: cos_sim_accuracy
            value: 99.8019801980198
          - type: cos_sim_ap
            value: 94.58629018512772
          - type: cos_sim_f1
            value: 89.84771573604061
          - type: cos_sim_precision
            value: 91.23711340206185
          - type: cos_sim_recall
            value: 88.5
          - type: dot_accuracy
            value: 99.74950495049505
          - type: dot_ap
            value: 92.5761214576951
          - type: dot_f1
            value: 87.09841917389087
          - type: dot_precision
            value: 88.86576482830385
          - type: dot_recall
            value: 85.39999999999999
          - type: euclidean_accuracy
            value: 99.80495049504951
          - type: euclidean_ap
            value: 94.56231673602272
          - type: euclidean_f1
            value: 90.02531645569621
          - type: euclidean_precision
            value: 91.17948717948718
          - type: euclidean_recall
            value: 88.9
          - type: manhattan_accuracy
            value: 99.8009900990099
          - type: manhattan_ap
            value: 94.5775591647447
          - type: manhattan_f1
            value: 89.86384266263238
          - type: manhattan_precision
            value: 90.64089521871821
          - type: manhattan_recall
            value: 89.1
          - type: max_accuracy
            value: 99.80495049504951
          - type: max_ap
            value: 94.58629018512772
          - type: max_f1
            value: 90.02531645569621
      - task:
          type: Classification
        dataset:
          type: mteb/toxic_conversations_50k
          name: MTEB ToxicConversationsClassification
          config: default
          split: test
          revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c
        metrics:
          - type: accuracy
            value: 67.43820000000001
          - type: ap
            value: 12.899489312331003
          - type: f1
            value: 52.03468121072981
      - task:
          type: Classification
        dataset:
          type: mteb/tweet_sentiment_extraction
          name: MTEB TweetSentimentExtractionClassification
          config: default
          split: test
          revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
        metrics:
          - type: accuracy
            value: 57.475947934352
          - type: f1
            value: 57.77676730676238
      - task:
          type: PairClassification
        dataset:
          type: mteb/twittersemeval2015-pairclassification
          name: MTEB TwitterSemEval2015
          config: default
          split: test
          revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
        metrics:
          - type: cos_sim_accuracy
            value: 83.94230196101806
          - type: cos_sim_ap
            value: 67.00916556336148
          - type: cos_sim_f1
            value: 63.046014257939085
          - type: cos_sim_precision
            value: 61.961783439490446
          - type: cos_sim_recall
            value: 64.16886543535621
          - type: dot_accuracy
            value: 83.18531322644095
          - type: dot_ap
            value: 63.112896030267066
          - type: dot_f1
            value: 59.06565656565657
          - type: dot_precision
            value: 56.63438256658596
          - type: dot_recall
            value: 61.715039577836414
          - type: euclidean_accuracy
            value: 83.94230196101806
          - type: euclidean_ap
            value: 67.19856676674463
          - type: euclidean_f1
            value: 63.08428413691571
          - type: euclidean_precision
            value: 58.9543682641596
          - type: euclidean_recall
            value: 67.83641160949868
          - type: manhattan_accuracy
            value: 83.91845979614949
          - type: manhattan_ap
            value: 66.9845327263072
          - type: manhattan_f1
            value: 62.693323274236135
          - type: manhattan_precision
            value: 59.884698534710544
          - type: manhattan_recall
            value: 65.77836411609499
          - type: max_accuracy
            value: 83.94230196101806
          - type: max_ap
            value: 67.19856676674463
          - type: max_f1
            value: 63.08428413691571
      - task:
          type: PairClassification
        dataset:
          type: mteb/twitterurlcorpus-pairclassification
          name: MTEB TwitterURLCorpus
          config: default
          split: test
          revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
        metrics:
          - type: cos_sim_accuracy
            value: 88.0777738968448
          - type: cos_sim_ap
            value: 84.19747786536
          - type: cos_sim_f1
            value: 75.91830995817077
          - type: cos_sim_precision
            value: 69.84671107949033
          - type: cos_sim_recall
            value: 83.14598090545118
          - type: dot_accuracy
            value: 87.14246904955951
          - type: dot_ap
            value: 82.37528804640529
          - type: dot_f1
            value: 74.40963166732163
          - type: dot_precision
            value: 69.4127841098447
          - type: dot_recall
            value: 80.18170619032954
          - type: euclidean_accuracy
            value: 88.08359529630924
          - type: euclidean_ap
            value: 84.22633217661986
          - type: euclidean_f1
            value: 76.09190339866403
          - type: euclidean_precision
            value: 72.70304390517605
          - type: euclidean_recall
            value: 79.81213427779488
          - type: manhattan_accuracy
            value: 88.08359529630924
          - type: manhattan_ap
            value: 84.18362004611083
          - type: manhattan_f1
            value: 76.08789625360231
          - type: manhattan_precision
            value: 71.49336582724072
          - type: manhattan_recall
            value: 81.3135201724669
          - type: max_accuracy
            value: 88.08359529630924
          - type: max_ap
            value: 84.22633217661986
          - type: max_f1
            value: 76.09190339866403
license: mit
language:
  - en

This is the sparse ONNX variant of the bge-small-en-v1.5 embeddings model created with DeepSparse Optimum for ONNX export and Neural Magic's Sparsify for One-Shot quantization and unstructured pruning (50%).

Current up-to-date list of sparse and quantized bge ONNX models:

zeroshot/bge-large-en-v1.5-sparse

zeroshot/bge-large-en-v1.5-quant

zeroshot/bge-base-en-v1.5-sparse

zeroshot/bge-base-en-v1.5-quant

zeroshot/bge-small-en-v1.5-sparse

zeroshot/bge-small-en-v1.5-quant