gMLP-large

Reported on 4 benchmarks across 3 tasks · 1 paper

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

Natural Language Processing4 results

Question AnsweringonSQuAD2.0
F1· 2021-05-17
78.3
best: 93.214 (IE-Net (ensemble))
Pay Attention to MLPs arXiv:2105.08050
Natural Language InferenceonMultiNLI
Matched· 2021-05-17
86.2
best: 92.6 (Turing NLR v5 XXL 5.4B (fine-tuned))
Pay Attention to MLPs arXiv:2105.08050
Natural Language InferenceonMultiNLI
Mismatched· 2021-05-17
86.5
best: 92.4 (Turing NLR v5 XXL 5.4B (fine-tuned))
Pay Attention to MLPs arXiv:2105.08050
Sentiment AnalysisonSST-2 Binary classification
Accuracy· 2021-05-17
94.8
best: 97.5 (T5-11B)
Pay Attention to MLPs arXiv:2105.08050