Back to List
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
Pythonallenai/reward-bench

reward-bench

RewardBench: the first evaluation tool for reward models.

63.3/100
711Forks: 95
View on GitHubHomepage →
Loading report...

Similar Projects

LlamaFactory

92

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Python70.5K

InternLM

67

Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).

Python7.2K

alignment-handbook

71

Robust recipes to align language models with human and AI preferences

Python5.6K

OpenClaw-RL

74

OpenClaw-RL: Train any agent simply by talking

Python5.1K
Back to List