---
datasets:
- OneThink/OneThinker-train-data
base_model:
- Qwen/Qwen3-VL-8B-Instruct
---

This repository contains the model presented in: [OneThinker: All-in-one Reasoning Model for Image and Video](https://arxiv.org/abs/2512.03043)

Code: https://github.com/tulerfeng/OneThinker