stanford-crfm / helm

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image models in Holistic Evaluation of Text-to-Image Models (HEIM) (https://arxiv.org/abs/2311.04287).
https://crfm.stanford.edu/helm
Apache License 2.0
1.77k stars 235 forks source link

Hacky fix for air bench headers #2720

Closed farzaank closed 1 month ago

farzaank commented 1 month ago

Updates the headers to have a list of strings that can be ignored (instead of just one). This includes the AIR Bench header.

yifanmai commented 1 month ago

Thanks!