OpenGVLab

/

InternVL2_5-1B

like 65

Follow

OpenGVLab 1.74k

This PR enhances the model card for InternVL2_5-1B by:

• Changing the main title to an H1 heading (# InternVL2_5-1B).
• Adding a prominent link to the primary paper: Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling, along with structured links to the GitHub repository and Hugging Face demo/project page. Related InternVL paper links are also grouped for better readability.
• Including the paper's abstract to provide users with a quick overview of the model's contributions directly on the Hub.
• Adding the qwen tag to the metadata, reflecting the model's base language model component (Qwen2.5-0.5B-Instruct) and improving its discoverability on the Hub.
• The existing "Quick Start" section already serves as a comprehensive sample usage guide and has been retained as is, complete with model loading, inference, multi-GPU, batch, and video inference examples.

These changes aim to make the model card more informative, discoverable, and user-friendly.