← 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.

75.1/100
★ 740Forks: 100
View on GitHub →Homepage →
Loading report...

Similar Projects

LlamaFactory

89

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

Python★ 75.0K

OpenClaw-RL

54

OpenClaw-RL: Train any agent simply by talking

Python★ 5.7K

alignment-handbook

74

Robust recipes to align language models with human and AI preferences

Python★ 5.7K

transformerlab-app

87

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

Python★ 5.2K
← Back to List