search

allenai / reward-bench

RewardBench: the first evaluation tool for reward models.
https://huggingface.co/spaces/allenai/reward-bench
Apache License 2.0
374 stars 47 forks source link

Fix llama3 quantization for DPO models #145

Closed natolambert closed 3 months ago

natolambert commented 3 months ago

@hamishivi noticed this by running the llama3 tulus ðŸ«