Improve model card: Add library, paper link, project page, and usage instructions

This PR significantly enhances the model card for better discoverability, usability, and adherence to Hugging Face best practices.

Key changes include:
* **Metadata update**:
* Added `library_name: transformers` to enable the "how to use" widget and improve model discoverability.
* Added `project_page: https://julienp.netlify.app/posts/soar/` to the metadata for structured information about the associated blog/project.
* **Content improvements**:
* Updated the paper link in the model card badges and main paper description to the official Hugging Face Paper page: [https://huggingface.co/papers/2507.14172](https://huggingface.co/papers/2507.14172).
* Added a prominent "GitHub" badge and a direct link to the official GitHub repository ([https://github.com/flowersteam/SOAR](https://github.com/flowersteam/SOAR)) for easier access to the code.
* Included the detailed installation instructions and "Run SOAR" guidance from the GitHub README, allowing users to get started directly from the Hugging Face Hub.
* Added a BibTeX citation section for proper academic attribution.

These updates aim to provide a more complete and accessible resource for users interacting with the SOAR-ARC model on the Hugging Face Hub.

README.md

@@ -1,11 +1,11 @@
 ---
+base_model:
+- mistralai/Mistral-Large-Instruct-2407
+datasets:
+- julien31/soar_arc_train_5M
 license: other
 license_name: mistral
 license_link: LICENSE
-datasets:
-- julien31/soar_arc_train_5M
-base_model:
-- mistralai/Mistral-Large-Instruct-2407
 pipeline_tag: text-generation
 tags:
 - text-generation
@@ -15,22 +15,26 @@ tags:
 - arc
 - arc-agi
 - soar
+library_name: transformers
+project_page: https://julienp.netlify.app/posts/soar/
 ---
+
 # SOAR-ARC Models: Self-Improving Language Models for Program Synthesis
 
 <p align="center">
-          🤗 <a href="https://huggingface.co/collections/julien31/soar-arc-6856d27681fce01d9af4c4a3">Hugging Face (data and model)</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://icml.cc/virtual/2025/poster/43499">Paper</a> &nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://julienp.netlify.app/posts/soar/">Blog</a>
+          🤗 <a href="https://huggingface.co/collections/julien31/soar-arc-6856d27681fce01d9af4c4a3">Hugging Face (data and model)</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://huggingface.co/papers/2507.14172">Paper</a> &nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://julienp.netlify.app/posts/soar/">Blog</a> &nbsp&nbsp | &nbsp&nbsp 🐙 <a href="https://github.com/flowersteam/SOAR">GitHub</a>
 </p>
 
 This repository contains one of the models fine-tuned using the **SOAR** (**S**elf-improving **O**perators for **A**utomated program **R**efinements) framework, as presented in the paper:
 
-> [**Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI**](https://icml.cc/virtual/2025/poster/43499)
+> [**Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI**](https://huggingface.co/papers/2507.14172)
 >
 > Julien Pourcel, Cédric Colas, Pierre-Yves Oudeyer.
 > *Proceedings of the 42nd International Conference on Machine Learning (ICML), 2025.*
 
 These models are specialized in solving tasks from the challenging [Abstraction and Reasoning Corpus (ARC)](https://github.com/fchollet/ARC) by synthesizing Python programs.
 
+**GitHub Repository**: [https://github.com/flowersteam/SOAR](https://github.com/flowersteam/SOAR)
 
 ## SOAR
 Large Language Models (LLMs) have become incredibly powerful, but they often hit a wall when faced with truly complex reasoning tasks that require discovering a solution from scratch. Simply throwing more computing power or using a bigger model often yields diminishing returns. But what if a model could learn from its own experience, getting smarter with every attempt?
@@ -71,4 +75,57 @@ For a complete, end-to-end example of how to format the prompt, run inference, e
 *   **Official SOAR GitHub Repository**: [https://github.com/flowersteam/SOAR](https://github.com/flowersteam/SOAR)
 *   **Inference & Visualization Notebook**: [https://github.com/flowersteam/SOAR/blob/main/notebook/inference_visualisation.ipynb](https://github.com/flowersteam/SOAR/blob/main/notebook/inference_visualisation.ipynb)
 
-<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/made with unsloth.png" width="20%" />
+<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/made%20with%20unsloth.png" width="20%" />
+
+## Installation
+
+### Conda Inference Environment
+```
+pip install --upgrade pip
+
+git clone https://github.com/flowersteam/SOAR
+cd SOAR
+conda create --name sglang47 \
+    python=3.11 \
+    -y
+conda activate sglang47
+
+pip install "sglang[all]>=0.4.7"
+
+pip install -e .
+pip install -r requirements
+
+```
+
+### Conda Training Environment
+```
+conda create --name unsloth_env \
+    python=3.11 \
+    pytorch-cuda=12.1 \
+    pytorch cudatoolkit xformers -c pytorch -c nvidia -c xformers \
+    -y
+conda activate unsloth_env
+
+pip install unsloth
+cd SOAR
+pip install -e .
+pip install -r requirements.txt
+```
+
+## Run SOAR
+To run SOAR, please refer to execution instructions located in the experience folder.
+
+For simple instructions on running sampling and refinement with SOAR, as well as exploring the dataset, please see the Jupyter notebooks provided in the `notebook` folder. These notebooks walk through the basic SOAR step, including how to generate candidate solutions, perform refinement, and analyze results. This hands-on guide will help you get started quickly and understand each step of the SOAR process.
+
+## Citation
+Please cite the following paper if you find this model useful for your research:
+
+```bibtex
+@inproceedings{pourcel2025selfimproving,
+  title={{Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI}},
+  author={Pourcel, Julien and Colas, C{\'e}dric and Oudeyer, Pierre-Yves},
+  booktitle={Proceedings of the 42nd International Conference on Machine Learning (ICML)},
+  year={2025},
+  url={https://huggingface.co/papers/2507.14172}
+}
+```