julien31

/

Soar-qwen-72b

like 0

This PR enhances the model card by:

• Updating the primary paper link in the header and body to the official Hugging Face Papers page (Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI) for better discoverability and integration within the Hub.
• Correcting the license to apache-2.0 as indicated by the base model's license (Qwen/Qwen2.5-72B-Instruct).
• Adding library_name: transformers to the metadata, which enables the "Use in Transformers" badge and relevant code snippets on the model page.
• Including a direct Python code snippet for basic inference, improving the "How to Use the Model" section with a clear, runnable example.
• Adding language: en and metrics: accuracy to the metadata for better categorization and searchability on the Hub.