MUPPET Roberta Large

Reported on 4 benchmarks across 4 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 AnsweringonBoolQ
Accuracy· 2021-01-26
87.5
best: 99.87 (Mistral-Nemo 12B (HPT))
Muppet: Massive Multi-task Representations with Pre-Finetuning arXiv:2101.11038
Common Sense ReasoningonCommonsenseQA
Accuracy· uses extra data· 2021-01-26
79.2
best: 92.54 (GPT-4o (HPT))
Muppet: Massive Multi-task Representations with Pre-Finetuning arXiv:2101.11038
Sentiment AnalysisonSST-2 Binary classification
Accuracy· 2021-01-26
97.4
best: 97.5 (T5-11B)
Muppet: Massive Multi-task Representations with Pre-Finetuning arXiv:2101.11038
Sentence CompletiononHellaSwag
Accuracy· 2021-01-26
86.4
best: 96.1 (CompassMTL 567M with Tailor)
Muppet: Massive Multi-task Representations with Pre-Finetuning arXiv:2101.11038