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

Minor fixes, new dockerfile, new models #144

Closed natolambert closed 5 months ago

natolambert commented 5 months ago

Closes #143, Closes #95, handles llama 3 not wanting to be quantized, adds quantization override.