Skip to content

Latest commit

 

History

History
125 lines (89 loc) · 4.37 KB

README.md

File metadata and controls

125 lines (89 loc) · 4.37 KB
Raw

OpenRM

OpenLLMAI logo

GitHub Contributors Issues Issues GitHub pull requests GitHub stars
Open-source / SOTA / Lightweight / Easy-to-use

[ English | 中文 ]

OpenRM: Exploring the State-of-the-Art in RM for RLHF and beyond:

Goals

  • SOTA RM: SOTA RM papers, implementation, modeling methods and tricks.
  • RM Data Engineering: Data is all you need, but not always.
  • best RM under 10B: Our ultimate goal is to provide easy-to-use RM models and services..
  • Academic contribution: Here there are many interesting things to do, good luck!

Dev logs

milestones:

Xianyu will be in charge of the development of the first version and the overall development plan. In the near future, we will also organize a series of closed-door RM discussions.

  • RM survey
  • RM modeling framework
  • RM modeling methods
  • RM training
  • RM server

Features

RM Modeling Support Matrix

Quick Start

Installation

Build your own RM

Start your RM server

Join Us

How to Join?

  1. Email us at [email protected] or join GitHub Organization. Please include the following details:
    • Your name
    • Your GitHub username
    • Your areas of interest
    • Your skills and experience related to NLP and/or AI
  2. You can also join us through the official GitHub OpenLLMAI ↗ project page. Just create an issue about your interest to contribute and we will get back to you.

What can you do?

  1. Join the team and participate in the development of the OpenLLMAI project.
  2. Contribute to the project by submitting pull requests.
  3. Help improve documentation, fix bugs, or create new features.
  4. Share the project and help us grow the community.

Sponsor Us

OpenRM is our new project from OpenLLMAI, thank you for your support! The OpenRLHF project that some people is familiar with has matured enough and is now developing independently,
transitioning from OpenLLMAI/OpenRLHF to OpenRLHF/OpenRLHF. Your sponsorship can help us maintain and improve OpenLLMAI. If you find this project useful, please consider sponsoring us. You can sponsor us on Open Collective ↗.

Starchart

Star History Chart

Contributors

A big thank you to all our contributors! If you want to contribute, feel free to make a pull request or create an issue.

References & Acknowledgements

We would like to express our gratitude to the following projects and organizations for their contributions to the field of AI and NLP:

Citation

@article{2024OpenLLMAI,
  title={OpenRM: Exploring the State-of-the-Art in RM for RLHF and beyond.},
  author={Xianyu,...},
  journal={},
  year={2024}
}

OpenLLMAI © 2024 OpenLLMAI. All Rights Reserved.