Improve model card: add metadata, paper link, GitHub link, and citation

This PR significantly improves the model card for the **Thinker** model by:
- Adding the `pipeline_tag: text-generation` for better discoverability on the Hub.
- Adding the `library_name: transformers` metadata tag, enabling the automated "How to use" widget, as the model is compatible with the `transformers` library.
- Linking to the official paper: [Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction](https://huggingface.co/papers/2511.07943).
- Including a direct link to the GitHub repository: [https://github.com/OpenSPG/KAG-Thinker](https://github.com/OpenSPG/KAG-Thinker).
- Adding the BibTeX citation provided in the project's README.

Please review and merge this PR.

README.md

@@ -1,3 +1,28 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction
+
+This repository contains the **KAG-Thinker-en-7b-instruct** model, which is part of the "Thinker" family of models, as presented in the paper [Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction](https://huggingface.co/papers/2511.07943).
+
+**Thinker** is a hierarchical thinking model for deep search through multi-turn interaction. It aims to enhance the reasoning abilities of LLMs by efficiently retrieving external knowledge bases and web pages. The model decomposes complex problems into independently solvable sub-problems, each dually represented in both natural language and an equivalent logical function to support knowledge base and web searches. Concurrently, dependencies between sub-problems are passed as parameters via these logical functions, enhancing the logical coherence of the problem-solving process. Thinker also performs knowledge boundary determination to avoid unnecessary external searches, allowing the LLM to answer directly when possible.
+
+For more details on the project, including installation, training, and inference instructions, please refer to the [GitHub repository](https://github.com/OpenSPG/KAG-Thinker).
+
+## Citation
+
+If you find our work useful, please consider citing:
+```bibtex
+@misc{zhang2025kagthinkerinteractivethinkingdeep,
+      title={KAG-Thinker: Interactive Thinking and Deep Reasoning in LLMs via Knowledge-Augmented Generation}, 
+      author={Dalong Zhang and Jun Xu and Jun Zhou and Lei Liang and Lin Yuan and Ling Zhong and Mengshu Sun and Peilong Zhao and QiWei Wang and Xiaorui Wang and Xinkai Du and YangYang Hou and Yu Ao and ZhaoYang Wang and Zhengke Gui and ZhiYing Yi and Zhongpu Bo},
+      year={2025},
+      eprint={2506.17728},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2506.17728}, 
+}
+```