OpenRLHF

Easy-to-use, scalable RLHF framework based on Ray. Supports PPO, GRPO, REINFORCE++, DAPO with vLLM integration and async training. Apache 2.0 licensed.

View on GitHub Unknown

Guide pending

We haven't written this guide yet.

Guides are drafted from the project's own README and metadata. Until one exists, check the product's repository and documentation for authoritative information.

Nearby on the map

Related projects

Oumi

oumi-ai/oumi

Fully open-source platform for the complete foundation model lifecycle - from data preparation and training to evaluation and deployment. Supports 100+ models with 200+ recipes for fine-tuning gpt-oss, Qwen3, DeepSeek-R1, and more. Apache 2.0 licensed.

unknown unknownactivity unknown

Marin

marin-community/marin

Open-source framework for foundation-model development with composable data, training, and evaluation pipelines for modern LLM research.

unknown unknownactivity unknown

LLaMA-Factory

hiyouga/LLaMA-Factory

One-stop unified framework for SFT, DPO, ORPO, KTO with web UI.

unknown unknownactivity unknown

Axolotl

axolotl-ai-cloud/axolotl

YAML-driven full pipeline for SFT, DPO, GRPO.

unknown unknownactivity unknown

ms-swift

modelscope/ms-swift

Unified training framework for 600+ LLMs and 300+ MLLMs with CPT/SFT/DPO/GRPO (AAAI 2025).

unknown unknownactivity unknown

Unsloth

unslothai/unsloth

2× faster, 70% less memory fine-tuning.

unknown unknownactivity unknown