Improve model card: Add pipeline tag, library name, and project page link

This PR improves the model card by adding:
- `pipeline_tag: image-text-to-text` to better categorize the model on the Hub.
- `library_name: transformers` to indicate compatibility with the Hugging Face Transformers library.
- A link to the official project page: https://omniverifier.github.io/.

Please review and merge if these additions are accurate.

README.md

@@ -1,9 +1,12 @@
 ---
-license: apache-2.0
 base_model:
 - Qwen/Qwen2.5-VL-7B-Instruct
+license: apache-2.0
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
-[Paper](https://arxiv.org/abs/2510.13804) | [Code](https://github.com/Cominclip/OmniVerifier)
+
+[Paper](https://arxiv.org/abs/2510.13804) | [Code](https://github.com/Cominclip/OmniVerifier) | [Project Page](https://omniverifier.github.io/)
 
 We introduce **Generative Universal Verifier**, a novel concept and plugin designed for next-generation multimodal reasoning in vision-language models and unified multimodal models, providing the fundamental capability of reflection and refinement on visual outcomes during the reasoning and generation process. 
 
@@ -13,7 +16,6 @@ We introduce **Generative Universal Verifier**, a novel concept and plugin desig
 
 OmniVerifier advances both reliable reflection during generation and scalable test-time refinement, marking a step toward more trustworthy and controllable next-generation reasoning systems.
 
-
 ```
 @article{zhang2025generative,
   author  = {Zhang, Xinchen and Zhang, Xiaoying and Wu, Youbin and Cao, Yanbin and Zhang, Renrui and Chu, Ruihang and Yang, Ling and Yang, Yujiu},