cornuHGF

/

LVR-SFT-VLPO-400

like 0

This PR adds a model card and metadata for the paper Leveraging Latent Visual Reasoning in Silence.

The card includes:

• Metadata for the image-text-to-text pipeline and transformers library.
• A brief description of the model and its training methodology.
• Links to the paper and the official GitHub repository.