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/Q-BERT (Shen et al., 2020)

Q-BERT (Shen et al., 2020)

Reported on 7 benchmarks across 4 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 Processing7 results

Natural Language InferenceonQNLI
Accuracy· 2019-09-12
93
best: 94.5 (PSQ (Chen et al., 2020))
SOTA
Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT arXiv:1909.05840
Natural Language InferenceonRTE
Accuracy· 2019-09-12
84.7
best: 86.8 (PSQ (Chen et al., 2020))
SOTA
Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT arXiv:1909.05840
Semantic Textual SimilarityonMRPC
Accuracy· 2019-09-12
88.2
best: 90.4 (PSQ (Chen et al., 2020))
SOTA
Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT arXiv:1909.05840
Linguistic AcceptabilityonCoLA
Accuracy· 2019-09-12
65.1
best: 82.7 (LTG-BERT-base 98M)
SOTA
Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT arXiv:1909.05840
Natural Language InferenceonMultiNLI
Matched· 2019-09-12
87.8
best: 92.6 (Turing NLR v5 XXL 5.4B (fine-tuned))
Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT arXiv:1909.05840
Semantic Textual SimilarityonSTS Benchmark
Pearson Correlation· 2019-09-12
0.911
best: 0.929 (MT-DNN-SMART)
Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT arXiv:1909.05840
Sentiment AnalysisonSST-2 Binary classification
Accuracy· 2019-09-12
94.8
best: 97.5 (T5-11B)
Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT arXiv:1909.05840