---
license: cc-by-nc-3.0
base_model:
- Qwen/Qwen2.5-VL-7B-Instruct
---

This repository contains the model used in the paper [Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning](https://huggingface.co/papers/2503.18013).

Code: https://github.com/jefferyZhan/Griffon