Improve model card: Add pipeline tag, library name, paper details, and sample usage

This PR significantly enhances the model card for `Agentic-R1` by:

* Adding `pipeline_tag: text-generation` to correctly categorize the model for text generation and reasoning tasks.
* Specifying `library_name: transformers` to enable the automated "How to use" widget, providing a convenient code snippet for users. This is supported by the model's `Qwen2ForCausalLM` architecture and `chat_template` in the `tokenizer_config.json`.
* Including the paper title and a direct link to the Hugging Face paper page: [Agentic-R1: Distilled Dual-Strategy Reasoning](https://huggingface.co/papers/2507.05707).
* Adding a link to the official GitHub repository for more details and code.
* Incorporating key features, dataset information, performance highlights, installation instructions, and a practical `transformers` sample usage snippet, making it easier for users to get started.

These changes will improve discoverability and usability for researchers and practitioners on the Hugging Face Hub.

README.md

@@ -1,9 +1,151 @@
 ---
-license: mit
+base_model:
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
 datasets:
 - VanishD/DualDistill
 language:
 - en
-base_model:
-- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
----
+license: mit
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# Agentic-R1: Distilled Dual-Strategy Reasoning
+
+This repository hosts the **Agentic-R1** model, an implementation of the paper [**Agentic-R1: Distilled Dual-Strategy Reasoning**](https://huggingface.co/papers/2507.05707).
+
+**Code**: https://github.com/StigLidu/DualDistill
+
+## Abstract
+
+Current long chain-of-thought (long-CoT) models excel at mathematical reasoning but rely on slow and error-prone natural language traces. Tool-augmented agents address arithmetic via code execution, but often falter on complex logical tasks. We introduce a fine-tuning framework, DualDistill, that distills complementary reasoning strategies from multiple teachers into a unified student model. Using this approach, we train Agentic-R1, which dynamically selects the optimal strategy for each query, invoking tools for arithmetic and algorithmic problems, and using text-based reasoning for abstract ones. Our method improves accuracy across a range of tasks, including both computation-intensive and standard benchmarks, demonstrating the effectiveness of multi-strategy distillation in achieving robust and efficient reasoning.
+
+## Key Features
+
+-   **Efficient Training**: Integrates tool use into long-chain-of-thought (CoT) reasoning using only 4 × A6000 GPUs
+-   **Unified Reasoning**: Fuses heterogeneous reasoning traces from multiple teacher models into a single student model
+
+<div align="center">
+  <img src="https://github.com/StigLidu/DualDistill/raw/main/fig/overview.png" alt="Overview of DualDistill" width="500">
+  <p><em>Overview of DualDistill methodology</em></p>
+</div>
+
+## Datasets
+
+| Dataset       | Description                                   | Link                                                 |
+| :------------ | :-------------------------------------------- | :--------------------------------------------------- |
+| **Training Set** | Complete training dataset with teacher trajectories | [🤗 HuggingFace](https://huggingface.co/datasets/VanishD/DualDistill) |
+| **Test Set**  | Evaluation benchmarks                         | `dataset/test/`                                      |
+
+## Results
+
+<div align="center">
+  <img src="https://github.com/StigLidu/DualDistill/raw/main/fig/result.png" alt="Performance comparison of Agentic-R1 models" width="700">
+</div>
+
+-   **Agentic-R1** demonstrates significant performance gains on **DeepMath-L** and **Combinatorics300**, where both complex reasoning and tool use are crucial for success.
+-   **Agentic-R1-SD** (Self-Distilled) further enhances performance through our self-distillation approach, consistently outperforming baseline models across nearly all evaluation tasks.
+
+## Quick Start
+
+### Installation
+
+1.  **Clone the repository**:
+    ```bash
+    git clone https://github.com/StigLidu/DualDistill.git
+    cd DualDistill
+    ```
+
+2.  **Create environment** (optional but recommended):
+    ```bash
+    conda create -n dualdistill python=3.11
+    conda activate dualdistill
+    ```
+
+3.  **Install dependencies**:
+    ```bash
+    pip install -r requirements.txt
+    pip install flash-attn --no-build-isolation
+    ```
+
+### Sample Usage
+
+Here's how to perform inference with the `Agentic-R1` model using the Hugging Face `transformers` library:
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "VanishD/Agentic-R1" # Or "VanishD/Agentic-R1-SD" for the self-distilled version
+
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16, # Use bfloat16 for better performance and memory if supported
+    device_map="auto",
+    trust_remote_code=True
+).eval() # Set model to evaluation mode
+
+# Prepare a simple user message
+messages = [{"role": "user", "content": "What is 123 + 456?"}]
+
+# Apply the chat template to format the prompt correctly for the model
+# The `add_generation_prompt=True` adds the Assistant token to prompt the model for its response.
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+
+# Encode the prompt
+input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
+
+# Generate response
+output_ids = model.generate(
+    input_ids,
+    max_new_tokens=256,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.95,
+    eos_token_id=tokenizer.eos_token_id,
+    pad_token_id=tokenizer.pad_token_id, # Often EOS token is used as PAD token for LLMs
+)
+
+# Decode and print the generated text, excluding the input prompt
+generated_text = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True).strip()
+print(f"Generated Text:
+{generated_text}")
+```
+
+## ⚠️ Important Notes
+
+-   **Code Execution Safety**: The evaluation scripts execute model-generated code locally. Only use trusted models before execution.
+-   **Inference Config**: If you are using vLLM (a recent version) and encounter an error regarding the maximum context length. You may need to modify the `model_max_length` in `tokenizer_config.json`.
+-   **Self-Distillation Warning**: The self-distillation step requires sampling many trajectories and can be time-consuming.
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](https://github.com/StigLidu/DualDistill/blob/main/LICENSE) file for details.
+
+## Acknowledgments
+
+We thank the following open-source projects for their foundational contributions:
+
+-   [OpenHands](https://github.com/All-Hands-AI/OpenHands) - Agent framework
+-   [DeepMath-103K](https://huggingface.co/datasets/zwhe99/DeepMath-103K) - Mathematical reasoning dataset
+-   [vLLM](https://github.com/vllm-project/vllm) - High-performance inference engine
+
+## Contact
+
+For questions or support, please contact:
+
+-   **Weihua Du**: [weihuad@cs.cmu.edu](mailto:weihuad@cs.cmu.edu)
+
+## Citation
+
+If you find our work useful, please consider citing:
+
+```bibtex
+@article{du2025agentic,
+  title={Agentic-R1: Distilled Dual-Strategy Reasoning},
+  author={Du, Weihua and Aggarwal, Pranjal and Welleck, Sean and Yang, Yiming},
+  journal={arXiv preprint arXiv:2507.05707},
+  year={2025}
+}
+```