This repos contains the biomedicine MLLM developed from Qwen2.5-VL-3B-Instruct in our paper: On Domain-Adaptive Post-Training for Multimodal Large Language Models. The correspoding training dataset is in biomed-visual-instructions.

Idle1211 year ago

Python

ZJU-AI4H/Hulu-Med-30A3

by ZJU-AI4H

image-text-to-text

Model

Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding

Active1833 months ago

Python

google/medgemma-1.5-4b-it

by google

image-text-to-text

Model

Active260.5K4 months ago

Python

google/medgemma-4b-pt

by google

image-text-to-text

Model

Idle1.1K11 months ago

Python

ZJU-AI4H/Hulu-Med-235A22

by ZJU-AI4H

image-text-to-text

Model

Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding

Active4723 months ago

Python