Create README.md

README.md

@@ -0,0 +1,37 @@
+---
+base_model:
+- Qwen/Qwen2.5-VL-72B-Instruct
+language:
+- en
+license: apache-2.0
+tags:
+- transformers
+- multimodal
+pipeline_tag: visual-question-answering
+---
+# VL-Rethinker-72B-Preview
+## Model Overview
+- **VL-Rethinker-72B-Preview** improves visual reasoning upon [Qwen2.5-VL-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct) model.
+
+- As of April 3rd, 2025, **VL-Rethinker-72B-Preview** achieves superior results on various visual reasoning benchmarks ([MathVision](https://mathllm.github.io/mathvision/),[MathVista](https://mathvista.github.io/),  [MathVerse](https://mathverse-cuhk.github.io/), [MMMU-Pro](), [EMMA](), [MEGA]()). 
+
+
+## Evaluation
+
+We will release a code repository for VLM evaluation. It supports RL training with simple rule-based rewards, meanwhile aligning with LLM-Judge results. 
+    
+Stay tuned!
+
+
+## Citation
+If you find our model useful, please consider citing:
+
+```
+@misc {VL-Rethinker-72B-Preview,
+	author       = { Wang, Haozhe and Lin, Fangzhen and Chen, Wuhu },
+	title        = { VL-Rethinker-72B-Preview },
+	year         = 2025,
+	url          = { https://huggingface.co/TIGER-Lab/VL-Rethinker-Preview},
+	publisher    = { Hugging Face }
+}
+```