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 __call__ for slicpairpm #128

Closed WeiXiongUST closed 6 months ago

WeiXiongUST commented 6 months ago

Now the test interface is consistent with custom classifier.

natolambert commented 6 months ago

@WeiXiongUST, quality again, sorry.

WeiXiongUST commented 6 months ago

@WeiXiongUST, quality again, sorry.

oh no.. A \n was missing at the end of the file and is added now.