HyperAI

Question Answering On Story Cloze

المقاييس

Accuracy

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج
Accuracy
Paper TitleRepository
GPT-3 175B (Few-Shot)87.7Language Models are Few-Shot Learners
Neo-6B (QA)76.3Ask Me Anything: A simple strategy for prompting language models
PaLM 2-M (one-shot)86.7PaLM 2 Technical Report
PaLM 2-S (one-shot)85.6PaLM 2 Technical Report
PaLM 2-L (one-shot)87.4PaLM 2 Technical Report
Neo-6B (QA + WS)87.8Ask Me Anything: A simple strategy for prompting language models
Neo-6B (few-shot)51.0Ask Me Anything: A simple strategy for prompting language models
0 of 7 row(s) selected.