Instructions to use microsoft/llava-med-7b-delta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/llava-med-7b-delta with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="microsoft/llava-med-7b-delta")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("microsoft/llava-med-7b-delta")
model = AutoModelForCausalLM.from_pretrained("microsoft/llava-med-7b-delta", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use microsoft/llava-med-7b-delta with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/llava-med-7b-delta"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/llava-med-7b-delta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/microsoft/llava-med-7b-delta

SGLang

How to use microsoft/llava-med-7b-delta with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "microsoft/llava-med-7b-delta" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/llava-med-7b-delta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "microsoft/llava-med-7b-delta" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/llava-med-7b-delta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use microsoft/llava-med-7b-delta with Docker Model Runner:
```
docker model run hf.co/microsoft/llava-med-7b-delta
```

tnaumann

bsnelling commited on Nov 24, 2025

Commit

50f8981

verified ·

1 Parent(s): 0dd1c26

Update README.md (#6)

Browse files

- Update README.md (d250f11c3c24ff66b2b9b16f54a95279eb11d073)

Co-authored-by: Blake S <bsnelling@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -257,3 +257,5 @@ If you find LLaVA-Med useful for your your research and applications, please cit
 - [BioMed CLIP](https://huggingface.co/microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224)
 - [Instruction Tuning with GPT-4](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM)

 - [BioMed CLIP](https://huggingface.co/microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224)
 - [Instruction Tuning with GPT-4](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM)
+## Data Summary
+https://huggingface.co/microsoft/llava-med-7b-delta/blob/main/data_summary_card.md