Instructions to use liuhaotian/llava-v1.6-mistral-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liuhaotian/llava-v1.6-mistral-7b with Transformers:

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

pipe = pipeline("image-text-to-text", model="liuhaotian/llava-v1.6-mistral-7b")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("liuhaotian/llava-v1.6-mistral-7b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use liuhaotian/llava-v1.6-mistral-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liuhaotian/llava-v1.6-mistral-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liuhaotian/llava-v1.6-mistral-7b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/liuhaotian/llava-v1.6-mistral-7b

SGLang

How to use liuhaotian/llava-v1.6-mistral-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 "liuhaotian/llava-v1.6-mistral-7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liuhaotian/llava-v1.6-mistral-7b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "liuhaotian/llava-v1.6-mistral-7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liuhaotian/llava-v1.6-mistral-7b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use liuhaotian/llava-v1.6-mistral-7b with Docker Model Runner:
```
docker model run hf.co/liuhaotian/llava-v1.6-mistral-7b
```

Potential ways to accelerate for image to text tasks?

#12

by triscuiter - opened Dec 6, 2024

Discussion

triscuiter

Dec 6, 2024

I have been trying to utilize this model for image-to-text tasks, and by far it seems that this model provides better qualities compared to other alternative models, such as Blip2 etc, regarding included details, accuracies and the ability of summarizing context. However the issue is it takes too much time, for me with a single image (resized to <= 300 for w/h) it will takes ~20-30 sec on average. I wonder if there's any possible ways to improve the inference process though? currently I have tried with 1 A10G with 24G mem or 4 A10G cards but seems the processing time doesn't change too much

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