Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/Q8BERT (Zafrir et al., 2019)

Q8BERT (Zafrir et al., 2019)

Reported on 7 benchmarks across 4 tasks · 1 paper · 2 SOTA

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

Natural Language Processing7 results

Natural Language InferenceonRTE
Accuracy· 2019-10-14
84.8
best: 86.8 (PSQ (Chen et al., 2020))
SOTA
Q8BERT: Quantized 8Bit BERT arXiv:1910.06188
Semantic Textual SimilarityonMRPC
Accuracy· 2019-10-14
89.7
best: 90.4 (PSQ (Chen et al., 2020))
SOTA
Q8BERT: Quantized 8Bit BERT arXiv:1910.06188
Natural Language InferenceonQNLI
Accuracy· 2019-10-14
93
best: 94.5 (PSQ (Chen et al., 2020))
Q8BERT: Quantized 8Bit BERT arXiv:1910.06188
Natural Language InferenceonMultiNLI
Matched· 2019-10-14
85.6
best: 92.6 (Turing NLR v5 XXL 5.4B (fine-tuned))
Q8BERT: Quantized 8Bit BERT arXiv:1910.06188
Semantic Textual SimilarityonSTS Benchmark
Pearson Correlation· 2019-10-14
0.911
best: 0.929 (MT-DNN-SMART)
Q8BERT: Quantized 8Bit BERT arXiv:1910.06188
Sentiment AnalysisonSST-2 Binary classification
Accuracy· 2019-10-14
94.7
best: 97.5 (T5-11B)
Q8BERT: Quantized 8Bit BERT arXiv:1910.06188
Linguistic AcceptabilityonCoLA
Accuracy· 2019-10-14
65
best: 82.7 (LTG-BERT-base 98M)
Q8BERT: Quantized 8Bit BERT arXiv:1910.06188