# microsoft/LLaVA-Med

Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

Repository: https://github.com/microsoft/LLaVA-Med
Canonical: https://ross.abutalabs.com/products/llava-med
Language: Python
License: NOASSERTION
License Family: other
Last push: 2025-06-04T15:56:12+00:00

## Health v2 (maintenance only)
Score: 40/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 25, release rhythm 35, longevity 85
- inputs: {"age_days": 1201, "days_push": 455, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2231, forks 294 (observed 2026-08-28T04:06:29.084135+00:00)

## What it is
LLaVA-Med is a large language-and-vision assistant fine-tuned for the biomedicine domain, built on the LLaVA multimodal architecture. It supports biomedical visual conversation and question answering over medical images, with checkpoints like llava-med-v1.5-mistral-7b available on Hugging Face.

## Use cases
- answer questions about medical images
- build a biomedical visual chatbot
- run visual question answering on radiology scans
- fine-tune a multimodal LLM for healthcare research
- chat with an assistant about biomedical figures
- evaluate a vision-language model on medical benchmarks

## When to choose
- you need a research-grade multimodal model specialized for biomedical images and text
- you want a ready-to-load medical VLM checkpoint without delta-weight patching
- you are doing biomedical visual question answering or conversation research

## When to avoid
- you need a model licensed for clinical or commercial deployment (research-only license)
- you need general-domain (non-medical) vision-language capabilities
- you require a permissively licensed model for production use

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-inference, llm-training, nlp, image-processing
- domain: artificial-intelligence, large-language-models, healthcare, computer-vision
- platform: python
- tags: multimodal, vision-language-model, biomedical, medical-imaging, visual-question-answering, instruction-tuning, research-license, natural-language-processing, linux, gpu

## Member repositories
- microsoft/LLaVA-Med (main) score 40

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:29.084135+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:44:28.612740+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/LLaVA-Med (fetched 2026-08-28T04:06:29.084135+00:00, sha 6c02f15cd5ac)
- Data as of 2026-08-30T08:39:29.467469+00:00.