Home› Projects› SimPO

SimPO

by princeton-nlp · GitHub

[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward

# alignment# large-language-models# preference-alignment# rlhf

⭐ Stars

956

🍴 Forks

📜 License

MIT

Commercial use OK

📅 Created

2024

🔄 Last commit

1 yr ago

🏷️ Category

alignment

💻 Language

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

📈 Star history

2026-07-202026-07-21

📄 About

[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward

❓ Frequently asked questions

[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward

SimPO is an open-source project. It is released under the MIT license.

Yes. SimPO is free and open source — you can use, modify and self-host it.

🏅 Maintainer of this project?

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![OpenSourceAI](https://opensourceai.tech/badge.php?tool=princeton-nlp-simpo)](https://opensourceai.tech/project/princeton-nlp-simpo.html)