trillionlabs

/

gWorld-8B

like 49

Follow

Trillion Labs 190

Hi! I'm Niels from the Hugging Face community science team. I've opened this PR to enhance your model card's discoverability and usability.

Specifically, I've made the following improvements:

• Added pipeline_tag: image-text-to-text to the YAML metadata, which accurately reflects the model's functionality of taking an image and text input to produce text output.
• Added library_name: transformers to the metadata, as indicated by the model's configuration and explicit usage of transformers.AutoProcessor in your GitHub README. This enables automated code snippets on the Hub.
• Linked the model card to the associated paper Generative Visual Code Mobile World Models on the Hugging Face platform. The existing arXiv link in the quick links has been preserved as per guidelines.
• Included a "Sample Usage" section with a Python code snippet for inference using vLLM, directly copied from your official GitHub repository to provide a ready-to-use example for users.
• Corrected the formatting of the citation block for better readability.

These updates aim to make your model easier to find and integrate for the community. Please let me know if you have any feedback!