GitLab

[Refactor] Fix Max Length arg

[Refactor] Benchmark scripts

Update README.md

[Refactor] Cleanup for `big-refactor`

[Refactor] Updated anthropic to new API

[Refactor] Fixes for when using `num_fewshot`

Merge branch 'big-refactor' of https://github.com/EleutherAI/lm-evaluation-harness into benchmark-scripts

[Refactor] Use console script

Remove condition to check for `winograd_schema`

Early stop bug of greedy_until (primary_until should be a list of str)

[Refactor] Migrate xwinograd tasks to yaml

[Refactor] Fix tests