---
license: mit
datasets:
- VLM-Reasoner/VerMulti
language:
- en
base_model:
- Qwen/Qwen2.5-VL-3B-Instruct
pipeline_tag: visual-question-answering
---


This repository contains the model presented in [LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL](https://huggingface.co/papers/2503.07536).

Project page: https://forjadeforest.github.io/LMM-R1-ProjectPage