Instructions to use LLaVA-VL/llava_plus_v0_7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLaVA-VL/llava_plus_v0_7b with Transformers:

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

pipe = pipeline("text-generation", model="LLaVA-VL/llava_plus_v0_7b")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("LLaVA-VL/llava_plus_v0_7b")
model = AutoModelForCausalLM.from_pretrained("LLaVA-VL/llava_plus_v0_7b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LLaVA-VL/llava_plus_v0_7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LLaVA-VL/llava_plus_v0_7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLaVA-VL/llava_plus_v0_7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LLaVA-VL/llava_plus_v0_7b

SGLang

How to use LLaVA-VL/llava_plus_v0_7b 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 "LLaVA-VL/llava_plus_v0_7b" \
    --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": "LLaVA-VL/llava_plus_v0_7b",
		"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 "LLaVA-VL/llava_plus_v0_7b" \
        --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": "LLaVA-VL/llava_plus_v0_7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LLaVA-VL/llava_plus_v0_7b with Docker Model Runner:
```
docker model run hf.co/LLaVA-VL/llava_plus_v0_7b
```

LLaVA-Plus Model Card

Model details

Model type: LLaVA-Plus: Large Language and Vision Assistants that Plug and Learn to Use Skills

Model date: LLaVA-Plus-v0-7b was trained in September 2023.

Paper or resources for more information: https://llava-vl.github.io/llava-plus/

Where to send questions or comments about the model: https://github.com/LLaVA-VL/LLaVA-Plus-Codebase/issues

Intended use

Primary intended uses: The primary use of LLaVA is research on large multimodal models and chatbots.

Primary intended users: The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.

Training dataset

https://huggingface.co/datasets/LLaVA-VL/llava-plus-data

Downloads last month: 20