EleutherAI/lm-evaluation-harness
14,220 3,679PythonMITUpdated 1 month ago
A framework for few-shot evaluation of language models.
evaluation-frameworklanguage-modeltransformer
Our verdict: worth borrowing ideas from
This framework provides a way to evaluate language models, which could be useful for extracting insights or methodologies relevant to local AI projects, even if not directly installable.
Filed under dev tooling in our directory.