allenai / reward-bench

RewardBench: the first evaluation tool for reward models.
https://huggingface.co/spaces/allenai/reward-bench
Apache License 2.0
440 stars 52 forks source link

Update the parameters of __call__ for Slic pair PM so that the test runs smoothly #127

Closed WeiXiongUST closed 6 months ago

WeiXiongUST commented 6 months ago

now it can be tested directly with the similar process of pairRM

natolambert commented 6 months ago

@WeiXiongUST can you rebase on main? I can't run the workflows as is (idk why)