OpenRLHF
/All repositories
Overview
HEALTH SCORE
Healthy*
Partial score (2/3 categories)
53out of 65
Solid maintainer coverage. Development cadence keeps the score from reaching Excellent. Security & Supply Chain is unavailable, so weights were redistributed.
LIFECYCLE
Active
Consistent commits, responsive maintainers, regular releases, and healthy issue triage.
Health breakdown
Healthy*(53/65)
Maintainer availability, known risks and supply chain posture, and whether the project is actively developed or appropriately stable.
Maintainer responsiveness
Median response time is 3 days.
Bus factor
7 active maintainers currently have merge rights.
Organization Diversity
Contributors span 222 organizations.
Project Achievements
Leaderboards
About
OpenRLHF is an open-source framework for fine-tuning large language models using reinforcement learning from human feedback (RLHF). It provides tools and implementations for training language models to align with human preferences through reward modeling and policy optimization.
First commit
Software value
$381K
Tags
large-language-models
openai-o1
proximal-policy-optimization
raylib
reinforcement-learning
reinforcement-learning-from-human-feedback
transformers
vllm
License(s)
Apache-2.0
Data sources
Git
GitHub