Medical Vision-Language Models
12 repos
Multimodal AI systems that combine vision and language understanding for medical imaging and clinical applications, particularly ECG (electrocardiogram) analysis and medical image interpretation. These repositories implement and extend large language models with medical-domain instruction tuning, grounding, and chat capabilities, leveraging architectures like LLaVA and techniques such as safetensors for efficient model storage and deployment in healthcare settings.
Python · 6
safetensors ·48
image-text-to-text ·48
llava_llama ·44
medical ·41
en ·41
ecg ·11
transformers ·7
endpoints_compatible ·7
text-generation ·7
reasoning ·4
