Improve model card: Add abstract for InternVL 2.5 paper
Hello!
To further improve the documentation for the InternVL2_5-1B-MPO model, I've added the abstract of its foundational paper, "Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling", directly to the model card.
This change aims to provide researchers and users with immediate context about the model's underlying research directly on the Hugging Face Hub, making it easier to understand its capabilities without needing to navigate to an external paper link.
All other aspects of the model card, including links to the GitHub repository and project page, detailed sample usage with transformers, and existing metadata, are already well-documented.
Let me know if you have any questions or suggestions!