tatsu-lab/alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

语言：Jupyter Notebook · GitHub 星标：2,023 · Fork：314

话题：deep-learning · evaluation · foundation-models · instruction-following · large-language-models · leaderboard · nlp · rlhf

在 GitHub 上查看原仓库