Mixed bag of fixes / updates - Githubissues

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

Mixed bag of fixes / updates #129

Closed natolambert closed 6 months ago

natolambert commented 6 months ago

Add RLHFFlow models to eval script,
add new GPT4 versions as a judge,
fix launch script
add prometheus 2 support