| license: apache-2.0 | |
| language: | |
| - en | |
| base_model: | |
| - Qwen/Qwen2.5-VL-3B-Instruct | |
| pipeline_tag: visual-question-answering | |
| datasets: | |
| - AI4Math/MathVista | |
| - AI4Math/MathVerse | |
| A Math ehanched Qwen 2.5VL 3B with VLM-R1 reinforcement learning. | |
| cite: arxiv.org/abs/2504.07615 |