Add model card for SimpleDeepSearcher

This PR adds a comprehensive model card for SimpleDeepSearcher, linking it to the paper [SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis](https://huggingface.co/papers/2505.16834).

It includes the `license`, `pipeline_tag`, and `library_name` metadata, making the model more discoverable and clearly indicating its compatibility with the Hugging Face `transformers` library. It also provides links to the official GitHub repository, the associated dataset, and other Hugging Face model checkpoints, along with a detailed overview and key contributions from the paper.

Please review and merge this PR.

README.md

@@ -0,0 +1,56 @@
+---
+license: mit
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis
+
+This repository contains the models and code for **SimpleDeepSearcher**, a lightweight yet effective framework for enhancing Large Language Models (LLMs) in complex deep search scenarios. As described in the paper [SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis](https://huggingface.co/papers/2505.16834), it bridges the gap in high-quality training trajectories by synthesizing realistic user interactions in live web search environments. This approach enables supervised fine-tuning (SFT) with only a small amount of curated data, achieving strong performance with significantly reduced computational cost and development complexity.
+
+<p align="center">
+  <img src="https://github.com/RUCAIBox/SimpleDeepSearcher/raw/main/assets/simplelog.jpg" alt="Example Image" width="550"/>
+</p>
+
+## Overview
+SimpleDeepSearcher is a lightweight yet effective framework for enhancing large language models (LLMs) in deep search tasks. Unlike traditional RAG or RL-based methods, SimpleDeepSearcher strategically synthesizes high-quality reasoning trajectories in real-world web environments, enabling supervised fine-tuning (SFT) with only a small amount of curated data. This results in strong performance with significantly reduced computational cost and development complexity.
+
+## Key Contributions
+
+- We propose a real web-based data synthesis framework that simulates realistic user search behaviors, generating multi-turn reasoning and search trajectories.
+- We design a multi-criteria data curation strategy that jointly optimizes both input question selection and output response filtering through orthogonal filtering dimensions.
+- Experimental results demonstrate that SFT on only 871 samples enables SimpleDeepSearcher to outperform strong baselines (especially RL-based baselines) on both in-domain and out-of-domain benchmarks.
+
+## Overall Performance
+
+<p align="center">
+  <img src="https://github.com/RUCAIBox/SimpleDeepSearcher/raw/main/assets/overall_performance.png" alt="Overall Performance" width="800"/>
+</p>
+
+## Associated Resources
+
+*   **Paper**: [SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis](https://huggingface.co/papers/2505.16834)
+*   **Code**: [GitHub Repository](https://github.com/RUCAIBox/SimpleDeepSearcher)
+*   **Dataset**: [0.8k-data-SimpleDeepSearcher](https://huggingface.co/datasets/RUC-AIBOX/0.8k-data-SimpleDeepSearcher)
+*   **Other Models**:\
+    *   [SimpleDeepSearcher-Qwen-7B](https://huggingface.co/RUC-AIBOX/Qwen-7B-SimpleDeepSearcher)
+    *   [SimpleDeepSearcher-Qwen-32B](https://huggingface.co/RUC-AIBOX/Qwen-32B-SimpleDeepSearcher)
+    *   [SimpleDeepSearcher-Dpsk-Distilled-Qwen-32B](https://huggingface.co/RUC-AIBOX/Dpsk-Distilled-Qwen-32B-SimpleDeepSearcher)
+    *   [SimpleDeepSearcher-QwQ-32B](https://huggingface.co/RUC-AIBOX/QwQ-32B-SimpleDeepSearcher)
+
+For detailed installation, data construction, training, and inference instructions, please refer to the [GitHub repository](https://github.com/RUCAIBox/SimpleDeepSearcher).
+
+## Citation
+Please kindly cite our report if they are helpful for your research.
+
+```bibtex
+@article{sun2025simpledeepsearcher,
+  title={SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis},
+  author={Sun, Shuang and Song, Huatong and Wang, Yuhao and Ren, Ruiyang and Jiang, Jinhao and Zhang, Junjie and Bai, Fei and Deng, Jia and Zhao, Wayne Xin and Liu, Zheng and others},
+  journal={arXiv preprint arXiv:2505.16834},
+  year={2025}
+}
+```
+
+## License
+This project is released under the [MIT License](https://github.com/RUCAIBox/SimpleDeepSearcher/blob/main/LICENSE).