search

allenai / reward-bench

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

Per token multiple rms #29

Closed khyathiraghavi closed 7 months ago

khyathiraghavi commented 7 months ago

Visualizing multiple rewards src="https://github.com/allenai/herm/assets/7048095/0e14b841-6f5a-45ae-a0db-0ab1959d7bfa">