PAPOGalaxy

/

PAPO-G-Qwen2.5-VL-3B

like 0

This PR significantly enhances the model card for PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning by:

• Adding the pipeline_tag: image-text-to-text, which accurately categorizes the model as a multimodal large language model capable of processing images and text to generate text. This improves its discoverability on the Hugging Face Hub (e.g., at https://huggingface.co/models?pipeline_tag=image-text-to-text).
• Specifying library_name: transformers, enabling the convenient "Use in Transformers" widget directly on the model page and providing standard loading instructions for users.
• Updating the paper link to the official Hugging Face Papers page (https://huggingface.co/papers/2507.06448) for better integration within the Hub's ecosystem.
• Including direct links to the project page (https://mikewangwzhl.github.io/PAPO/) and the GitHub repository (https://github.com/mikewangwzhl/PAPO) for users to find more context and the source code.
• Adding a practical Python code snippet for inference using the transformers library, allowing users to quickly get started with the model.

These updates aim to provide a more comprehensive, user-friendly, and discoverable model card.