ecoxial2007

/

CheX-Phi4MM-GRPO

like 1

This PR significantly improves the model card for the CheXPO-v2 model (implemented as CheX-Phi4MM) by adding crucial metadata and expanding the content for better discoverability and user information.

The changes include:

• Adding pipeline_tag: image-text-to-text to accurately reflect the model's multimodal capabilities (processing images and text to generate text outputs), enhancing its visibility on the Hub.
• Adding library_name: transformers as the model's configuration (config.json, tokenizer_config.json) indicates compatibility with the Hugging Face transformers library, which will enable the automated "how to use" code snippet.
• Providing a clear link to the paper: CheXPO-v2: Preference Optimization for Chest X-ray VLMs with Knowledge Graph Consistency.
• Including a link to the official GitHub repository: https://github.com/ecoxial2007/CheX-Phi4MM.
• Adding a concise overview of the model and its key contributions.

Please review and merge these improvements.