IDEFICS3_ROCO: Medical Image to Text running on cpu

This model generates a description of a medical image.

This demo is based on the IDEFICS3_ROCO model, which is a multimodal model that can generate text from images. It has been fine-tuned on eltorio/ROCO-radiology a dataset of medical images and can generate descriptions of medical images. Try uploading an image of a medical image and see what the model generates!
🐢 This model is running on cpu it will be very (very) slow. If you can donate some GPU time it will be usable 🐢. Please contact us.
2024 - Ronan Le Meillat