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")

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
```

Do delta weights work if used with llama 2 ?

by denisparra - opened Dec 19, 2023

Discussion

denisparra

Dec 19, 2023

Hi! I want to use llava-med which requires first downloading Llama original weights to be update with llama-med-delta.
I was wondering id these delta weights would work with llama2-7b weights or only the the original llama-7b weights?

Thanks!

Denis

filbel

Jul 22, 2025

This comment has been hidden (marked as Resolved)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment