allenai / reward-bench

RewardBench: the first evaluation tool for reward models.
https://huggingface.co/spaces/allenai/reward-bench
Apache License 2.0
301 stars 32 forks source link

Add bfloat16 support natively #155

Closed natolambert closed 2 weeks ago

natolambert commented 2 weeks ago

Also, rerunning models for: