OpenLMLab/MOSS-RLHF
Research framework for training and aligning large language models using Reinforcement Learning from Human Feedback (RLHF) with PPO.
Not currently ranked — collecting fresh signals.
star history
MOSS-RLHF is a research project focused on RLHF techniques for aligning large language models. Part I covers Proximal Policy Optimization (PPO) implementation for LLM fine-tuning, while Part II addresses reward modeling. The project provides code for training reward models and has released annotated datasets including a cleaned hh-rlhf dataset. It won the best paper award at NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following.
Frequently asked
- What is OpenLMLab/MOSS-RLHF?
- Research framework for training and aligning large language models using Reinforcement Learning from Human Feedback (RLHF) with PPO.
- Is MOSS-RLHF open source?
- Yes — OpenLMLab/MOSS-RLHF is open source, released under the Apache-2.0 license.
- What language is MOSS-RLHF written in?
- OpenLMLab/MOSS-RLHF is primarily written in Python.
- How popular is MOSS-RLHF?
- OpenLMLab/MOSS-RLHF has 1.4k stars on GitHub.
- Where can I find MOSS-RLHF?
- OpenLMLab/MOSS-RLHF is on GitHub at https://github.com/OpenLMLab/MOSS-RLHF.