README.md

metadata

library_name: transformers
datasets:
  - flaviagiammarino/vqa-rad
  - mdwiratathya/SLAKE-vqa-english
  - agupte/MedVQA
base_model:
  - microsoft/llava-med-v1.5-mistral-7b

LLaVA-Med-Radiology

This is a fine-tuned version of LLaVA on the VQA-RAD, SLAKE, and MedVQA datasets for medical image-based visual question answering (VQA).

Model Description

LoRA fine-tuned on the VQA-RAD, SLAKE, and MedVQA datasets for radiology image analysis and visual question answering. These datasets contain radiology images (X-rays, CT scans, etc.) paired with questions and answers, focusing on medical interpretations of these images.