# uclaml/spin

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/uclaml-spin).**

1,245 stars · 105 forks · Python · Apache-2.0

## Links

- GitHub: https://github.com/uclaml/SPIN
- Homepage: https://uclaml.github.io/SPIN/
- awesome-repositories: https://awesome-repositories.com/repository/uclaml-spin.md

## Topics

`deep-learning` `fine-tuning` `large-language-models` `self-play`

## Description

The official implementation of Self-Play Fine-Tuning (SPIN)

## Tags

### Part of an Awesome List

- [Reinforcement Learning](https://awesome-repositories.com/f/awesome-lists/ai/reinforcement-learning.md) — Self-play fine-tuning to enhance language model performance.
- [Self-Improvement Methods](https://awesome-repositories.com/f/awesome-lists/ai/self-improvement-methods.md) — Uses self-play to refine language models without external human data.