Add model card and metadata
Hi! I'm Niels from the Hugging Face community team. I noticed this repository is currently a placeholder.
This PR adds a proper model card, linking it to the research paper Comprehensive language-image pre-training for 3D medical image understanding, and includes the relevant pipeline_tag metadata to improve discoverability on the Hub.
Hi, @nielsr . Thanks for your contribution (not sure whether this PR was automated).
The whole repo is actually ready, with a comprehensive model card etc. I'm just waiting for our legal team to give us the green light, which will hopefully happen within days from now, so I can push everything to the hub.
Can you help me understand why we need the image-text-to-text pipeline tag? This is basically a CLIP model for CT scans.
Ok, yeah that tag is mainly used for VLMs. For CLIP-like models, we usually use zero-shot-image-classification: https://huggingface.co/models?pipeline_tag=zero-shot-image-classification&sort=trending