Improve model card for MagicAssessor-7B: Add pipeline tag, library name, and links

README.md

@@ -1,18 +1,19 @@
 ---
-license: mit
 base_model:
 - Qwen/Qwen2.5-VL-7B-Instruct
+license: mit
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
 
-Paper:
-MagicMirror: A Large-Scale Dataset and Benchmark for Fine-Grained Artifacts Assessment in Text-to-Image Generation
-https://arxiv.org/abs/2509.10260
+# MagicAssessor-7B
 
-Dataset:
-https://huggingface.co/datasets/wj-inf/MagicData340k
+MagicAssessor-7B is a Vision-Language Model (VLM) developed for fine-grained artifact assessment in text-to-image generation. It is a core component of the comprehensive **MagicMirror** framework, which aims to systematically evaluate the perceptual quality and identify various anatomical and structural flaws in generated images.
 
-Model:
-https://huggingface.co/datasets/wj-inf/MagicAssessor-7B
+The model was introduced in the paper [MagicMirror: A Large-Scale Dataset and Benchmark for Fine-Grained Artifacts Assessment in Text-to-Image Generation](https://arxiv.org/abs/2509.10260).
 
-Benchmark:
-https://github.com/wj-inf/MagicMirror
+*   **Paper**: [arXiv:2509.10260](https://arxiv.org/abs/2509.10260) | [Hugging Face Papers: 2509.10260](https://huggingface.co/papers/2509.10260)
+*   **Project Page**: https://wj-inf.github.io/MagicMirror-page/
+*   **Code / GitHub Repository (MagicMirror Benchmark)**: https://github.com/wj-inf/MagicMirror
+*   **Dataset (MagicData340K)**: https://huggingface.co/datasets/wj-inf/MagicData340k
+*   **Model (MagicAssessor-7B - this repository)**: https://huggingface.co/wj-inf/MagicAssessor-7B