---
base_model:
- Qwen/Qwen2.5-VL-7B-Instruct
datasets:
- kolerk/TON-Math-SFT
language:
- en
license: apache-2.0
metrics:
- accuracy
pipeline_tag: image-text-to-text
library_name: transformers
---

This is the model cited in the paper: [Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models](https://arxiv.org/abs/2505.16854).

Code: https://github.com/kokolerk/TON