MagicXin

/

DCFormer_SigLIP

like 0

This PR enhances the model card for Med3DVLM by:

• Linking it to the paper Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis.
• Adding the pipeline_tag: image-text-to-text for better discoverability.
• Specifying library_name: transformers as the model is compatible with the Transformers library.
• Adding a sample usage snippet from the GitHub README to demonstrate inference.

Please review these additions.