InternRobotics

/

InternVLA-M1-LIBERO-Goal

like 12

Follow

Intern Robotics 229

This PR significantly improves the model card for InternVLA-M1_object by:

• Adding pipeline_tag: robotics: This helps users discover the model more easily on the Hugging Face Hub, aligning with the model's core function for generalist robot policy.
• Correcting the license to mit: This aligns with the official LICENSE specified in the project's GitHub repository, replacing the previously listed cc-by-nc-sa-4.0.
• Including the paper link directly in the introductory paragraph: InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy.
• Adding the paper abstract: Providing a concise overview of the model's methodology and results for quick understanding.
• Integrating the teaser.png image: Enhancing the visual presentation of the model card.
• Introducing a "Sample Usage" section: With Python code snippets for both chat (image Q&A / spatial grounding) and action prediction, derived directly from the GitHub README to make the model easier to use.
• Adding the "Acknowledgements" section: Providing proper attribution to projects that inspired this work.
• Updating the Citation: Using the @article BibTeX format from the GitHub README and including the Hugging Face paper URL.

These changes will make the model card more informative, discoverable, and user-friendly for the community.