← 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.

58.8/100
★ 720Forks: 99
View on GitHub →Homepage →
Loading report...

Similar Projects

LlamaFactory

92

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

Python★ 72.0K

alignment-handbook

71

Robust recipes to align language models with human and AI preferences

Python★ 5.6K

OpenClaw-RL

68

OpenClaw-RL: Train any agent simply by talking

Python★ 5.5K

transformerlab-app

89

The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.

Python★ 5.1K
← Back to List