# contextualai/halos

**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/contextualai-halos).**

906 stars · 52 forks · Python · Apache-2.0

## Links

- GitHub: https://github.com/ContextualAI/HALOs
- Homepage: https://arxiv.org/abs/2402.01306
- awesome-repositories: https://awesome-repositories.com/repository/contextualai-halos.md

## Topics

`alignment` `dpo` `halos` `kto` `ppo` `rlhf`

## Description

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

## Tags

### Part of an Awesome List

- [Reinforcement Learning](https://awesome-repositories.com/f/awesome-lists/ai/reinforcement-learning.md) — Model alignment using prospect theoretic optimization.