Instructions to use Qwen/Qwen2-VL-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen2-VL-7B-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="Qwen/Qwen2-VL-7B-Instruct")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")
model = AutoModelForImageTextToText.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Qwen/Qwen2-VL-7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen2-VL-7B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qwen/Qwen2-VL-7B-Instruct",
		"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/Qwen/Qwen2-VL-7B-Instruct

SGLang

How to use Qwen/Qwen2-VL-7B-Instruct 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 "Qwen/Qwen2-VL-7B-Instruct" \
    --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": "Qwen/Qwen2-VL-7B-Instruct",
		"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 "Qwen/Qwen2-VL-7B-Instruct" \
        --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": "Qwen/Qwen2-VL-7B-Instruct",
		"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 Qwen/Qwen2-VL-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen2-VL-7B-Instruct
```

Anyone able to deploy an inference endpoint on sagemaker?

#71

by TeoGX - opened Jan 10, 2025

Discussion

TeoGX

Jan 10, 2025

Unable to deploy an inference endpoint on sagemaker with suggested script

models

hub = {
'HF_MODEL_ID':'Qwen/Qwen2-VL-7B-Instruct',
'SM_NUM_GPUS': json.dumps(1)
}

create Hugging Face Model Class

huggingface_model = HuggingFaceModel(
image_uri=get_huggingface_llm_image_uri("huggingface",version="2.3.1"),
env=hub,
role=role,
)

deploy model to SageMaker Inference

predictor = huggingface_model.deploy(
initial_instance_count=1,
instance_type="ml.g5.8xlarge",
container_startup_health_check_timeout=300,
)

Saurabh-hiehq

Jan 23, 2025

not able to deploy,it is throwing qwen2-vl not supported

pagezyhf

Jan 23, 2025

Hey hey,

here is a command deployment that works:

image_uri = "763104351884.dkr.ecr.us-east-1.amazonaws.com/huggingface-pytorch-tgi-inference:2.4.0-tgi3.0.1-gpu-py311-cu124-ubuntu22.04"
model_name = "qwen2-vl-7b-instruct" + time.strftime("%Y-%m-%d-%H-%M-%S", time.gmtime())

hub = {
'HF_MODEL_ID': 'Qwen/Qwen2-VL-7B-Instruct',
'SM_NUM_GPUS': json.dumps(1),
'MESSAGES_API_ENABLED': "true",
'CUDA_GRAPHS': json.dumps(0),
}

model = HuggingFaceModel(
name=model_name,
env=hub,
role=role,
image_uri=image_uri
)

predictor = model.deploy(
initial_instance_count=1,
instance_type="ml.g5.2xlarge",
endpoint_name=model_name
)

input_data = {
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{
"role": "user",
"content": [
{"type": "text", "text": "Whats in this image?"},
{
"type": "image_url",
"image_url": {
"url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/rabbit.png"
},
},
],
}
]
}

predictor.predict(input_data)

A few comments:

it uses the latest TGI image available in AWS, it will soon be updated and accessible from the Sagemaker SDK
There is an issue opened here : https://github.com/huggingface/text-generation-inference/issues/2823. As a workaround I'm specifying CUDA_GRAPHS=0

Hope it helps!
cheers

Saurabh-hiehq

Jan 24, 2025

•

edited Jan 24, 2025

Hi pagezyhf,will above code work for "OS-Copilot/OS-Atlas-Base-7B" also?????

can i create or have my own image uri.

pagezyhf

Jan 24, 2025

"OS-Copilot/OS-Atlas-Base-7B" this model requires the flag to run remote code (trust_remote_code : "true") but appart from that, it should work. Give it a try and let me know!

TeoGX

Jan 25, 2025

@pagezyhf Thank you, working as intended! Any possibility this would also work for Qwen2-VL-72B instruct on a larger instance?

pagezyhf

Jan 27, 2025

"Any possibility this would also work for Qwen2-VL-72B instruct on a larger instance?"
Yes it should work with a larger instance!

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