Zhang199

/

EDGE-GRPO-Qwen-7B

like 1

This PR significantly enhances the model card by:

• Adding pipeline_tag: text-generation, library_name: transformers, and relevant tags (qwen2, llm, reinforcement-learning, reasoning) to the metadata for improved discoverability and functionality.
• Incorporating comprehensive information from the associated GitHub repository, including the project overview, news, installation instructions, performance results, and citation details.
• Providing a runnable Python usage example for both standard text generation and chat completion using the transformers library.
• Adding a direct link to the Hugging Face paper page.
• Removing the irrelevant "File information" section from the model card.