Improve model card: Add library_name, detailed usage, and GitHub link

This PR significantly enhances the model card for `OpenCausaLab/CauSight` by:

- Adding `library_name: transformers` to the metadata, which enables the "how to use" widget on the Hugging Face Hub, based on the `config.json` and `tokenizer_config.json` files.
- Providing a brief description of the model, summarizing its purpose and capabilities from the paper's abstract.
- Adding a direct link to the official GitHub repository for code and project details.
- Including detailed "User Guide" sections for setup, dataset download, model download, and evaluation, directly extracted from the GitHub README.
- Adding a BibTeX citation for proper academic attribution.

These changes make the model card more informative, user-friendly, and compliant with best practices on the Hugging Face Hub.

README.md

@@ -1,12 +1,96 @@
 ---
-license: apache-2.0
-language:
-- en
 base_model:
 - Qwen/Qwen2.5-VL-7B-Instruct
+language:
+- en
+license: apache-2.0
 pipeline_tag: image-text-to-text
+library_name: transformers
 ---
 
+# CauSight: Learning to Supersense for Visual Causal Discovery
+
+This repository contains the **CauSight** model, a novel vision-language model designed to perform visual causal discovery through causally aware reasoning. CauSight enables AI systems to infer cause-and-effect relations among visual entities across diverse scenarios, moving beyond mere perception. It integrates training data curation, Tree-of-Causal-Thought (ToCT) for synthesizing reasoning trajectories, and reinforcement learning with a designed causal reward. Experiments demonstrate that CauSight significantly outperforms models like GPT-4.1 on visual causal discovery.
+
 This work is introduced in the following paper:
 
-**CauSight: Learning to Supersense for Visual Causal Discovery**  [📄 arXiv](https://arxiv.org/abs/2512.01827)
+**[CauSight: Learning to Supersense for Visual Causal Discovery](https://arxiv.org/abs/2512.01827)** [📄 arXiv]
+
+**Project Page and Code:** [https://github.com/OpenCausaLab/CauSight](https://github.com/OpenCausaLab/CauSight)
+
+## 🔧 User Guide
+
+### 1. Clone the Repository
+
+```bash
+git clone https://github.com/OpenCausaLab/CauSight.git
+cd CauSight
+```
+
+### 2. Set Up the Environment
+
+We recommend using **conda**:
+
+```bash
+conda create -n causight python=3.10
+conda activate causight
+
+pip install -r requirements.txt
+pip install -e .
+```
+
+### 3. Download the Dataset (VCG-32K)
+
+```bash
+mkdir -p VCG-32K
+pip install huggingface_hub
+
+hf login
+hf download OpenCausaLab/VCG-32K \
+    --repo-type dataset \
+    --local-dir ./VCG-32K
+```
+
+```bash
+tar -xzf ./VCG-32K/COCO/images.tar.gz -C ./VCG-32K/COCO
+tar -xzf ./VCG-32K/365/images.tar.gz -C ./VCG-32K/365
+```
+
+### 4. Download the CauSight Model
+
+```bash
+mkdir -p model
+huggingface-cli download OpenCausaLab/CauSight \
+    --repo-type model \
+    --local-dir ./model
+```
+
+### 5. Evaluation
+
+Start the model server, then run inference:
+
+```bash
+bash model_server.sh
+python run_inference.py
+```
+
+### 6. Tree-of-Causal-Thought (If you want to make your own SFT data with ToCT.)
+
+```bash
+bash model_server.sh
+python run.py
+```
+
+## Citation
+
+If you find our work helpful or inspiring, please consider citing it:
+
+```bibtex
+@article{zhang2025causight,
+  title={CauSight: Learning to Supersense for Visual Causal Discovery},
+  author={Zhang, Yize and Chen, Meiqi and Chen, Sirui and Peng, Bo and Zhang, Yanxi and Li, Tianyu and Lu, Chaochao},
+  journal={arXiv preprint arXiv:2512.01827},
+  year={2025},
+  url={https://arxiv.org/abs/2512.01827}
+}
+```