EleutherAI/lm-evaluation-harness

A framework for few-shot evaluation of language models.

1 best points · 0 comments · 2 Hacker News posts · 14,421 GitHub stars · View on GitHub

Hacker News discussions

• Language Model Evaluation Harness (1 points, 0 comments, by tosh, 2023-11-25)
• Show HN: EleutherAI / Lm-Evaluation-Harness (1 points, 0 comments, by marvinified, 2026-05-13)