microsoft/LLaVA-Med
A multimodal large language-and-vision assistant trained specifically for biomedical applications, published at NeurIPS 2023.
Not currently ranked — collecting fresh signals.
star history
LLaVA-Med is a large language-and-vision assistant built for the biomedicine domain, trained using visual instruction tuning to achieve multimodal GPT-4 level capabilities. It combines vision and language understanding to interpret medical images and answer related queries. The model is available on Hugging Face and supports direct loading without delta weights.
Frequently asked
- What is microsoft/LLaVA-Med?
- A multimodal large language-and-vision assistant trained specifically for biomedical applications, published at NeurIPS 2023.
- Is LLaVA-Med open source?
- Yes — microsoft/LLaVA-Med is an open-source project tracked on heatdrop.
- What language is LLaVA-Med written in?
- microsoft/LLaVA-Med is primarily written in Python.
- How popular is LLaVA-Med?
- microsoft/LLaVA-Med has 2.2k stars on GitHub.
- Where can I find LLaVA-Med?
- microsoft/LLaVA-Med is on GitHub at https://github.com/microsoft/LLaVA-Med.