SimPO
[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
Optimize preferences for AI models without needing a reference model, improving their performance on various tasks.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytime[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
SimPO has 958 stars on GitHub. It has been forked 78 times. SimPO is written mainly in Python. It has been in active development since 2024. SimPO is available under the MIT license. Its main topics are alignment, large-language-models, preference-alignment, rlhf.
What is SimPO?
[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
Is SimPO open source?
SimPO is an open-source project. It is released under the MIT license.
Is SimPO free?
Yes. SimPO is free and open source — you can use, modify and self-host it.
What license does SimPO use?
SimPO is available under the MIT license.
What language is SimPO written in?
SimPO is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/princeton-nlp-simpo.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.