TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/TinyBERT-6 67M

TinyBERT-6 67M

Reported on 11 benchmarks across 5 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing11 results

  • Natural Language InferenceonMultiNLI Dev
    Matched· 2019-09-23
    84.5
    SOTA
    TinyBERT: Distilling BERT for Natural Language UnderstandingarXiv:1909.10351
  • Natural Language InferenceonMultiNLI Dev
    Mismatched· 2019-09-23
    84.5
    SOTA
    TinyBERT: Distilling BERT for Natural Language UnderstandingarXiv:1909.10351
  • Semantic Textual SimilarityonMRPC Dev
    Accuracy· 2019-09-23
    86.3
    best: 91.2 (Synthesizer (R+V))
    SOTA
    TinyBERT: Distilling BERT for Natural Language UnderstandingarXiv:1909.10351
  • Linguistic AcceptabilityonCoLA Dev
    Accuracy· 2019-09-23
    54
    best: 88.6 (En-BERT + TDA)
    SOTA
    TinyBERT: Distilling BERT for Natural Language UnderstandingarXiv:1909.10351
  • Question AnsweringonSQuAD1.1 dev
    EM· 2019-09-23
    79.7
    best: 90.06 (T5-11B)
    TinyBERT: Distilling BERT for Natural Language UnderstandingarXiv:1909.10351
  • Question AnsweringonSQuAD1.1 dev
    F1· 2019-09-23
    87.5
    best: 95.77 (XLNet+DSC)
    TinyBERT: Distilling BERT for Natural Language UnderstandingarXiv:1909.10351
  • Question AnsweringonSQuAD2.0 dev
    EM· 2019-09-23
    69.9
    best: 87.9 (XLNet (single model))
    TinyBERT: Distilling BERT for Natural Language UnderstandingarXiv:1909.10351
  • Question AnsweringonSQuAD2.0 dev
    F1· 2019-09-23
    73.4
    best: 90.6 (XLNet (single model))
    TinyBERT: Distilling BERT for Natural Language UnderstandingarXiv:1909.10351
  • Natural Language InferenceonMultiNLI
    Matched· 2019-09-23
    84.6
    best: 92.6 (Turing NLR v5 XXL 5.4B (fine-tuned))
    TinyBERT: Distilling BERT for Natural Language UnderstandingarXiv:1909.10351
  • Natural Language InferenceonMultiNLI
    Mismatched· 2019-09-23
    83.2
    best: 92.4 (Turing NLR v5 XXL 5.4B (fine-tuned))
    TinyBERT: Distilling BERT for Natural Language UnderstandingarXiv:1909.10351
  • Sentiment AnalysisonSST-2 Binary classification
    Accuracy· 2019-09-23
    93.1
    best: 97.5 (T5-11B)
    TinyBERT: Distilling BERT for Natural Language UnderstandingarXiv:1909.10351