FLAN-T5-Large 783M

Reported on 5 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 Processing5 results

Question AnsweringonPIQA
Accuracy· 2023-04-27
72.2
best: 90.1 (Unicorn 11B (fine-tuned))
LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions arXiv:2304.14402
Question AnsweringonOpenBookQA
Accuracy· 2023-04-27
31.2
best: 95.9 (GPT-4 + knowledge base)
LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions arXiv:2304.14402
Common Sense ReasoningonWinoGrande
Accuracy· 2023-04-27
59.9
best: 96.1 (ST-MoE-32B 269B (fine-tuned))
LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions arXiv:2304.14402
Word Sense DisambiguationonWords in Context
Accuracy· 2023-04-27
64.7
best: 85.3 (COSINE + Transductive Learning)
LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions arXiv:2304.14402
Sentence CompletiononHellaSwag
Accuracy· 2023-04-27
48.7
best: 96.1 (CompassMTL 567M with Tailor)
LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions arXiv:2304.14402