Instructions to use hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4")
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("hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4")
model = AutoModelForImageTextToText.from_pretrained("hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4")
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

vLLM

How to use hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4",
		"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/hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4

SGLang

How to use hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4 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 "hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4" \
    --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": "hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4",
		"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 "hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4" \
        --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": "hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4",
		"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 hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4 with Docker Model Runner:
```
docker model run hf.co/hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4
```

What is the minimum GPU usage for the Qwen2.5-VL-7B-Instruct-GPTQ-Int4?

by Xtracta-Qiming - opened Mar 12, 2025

Discussion

Xtracta-Qiming

Mar 12, 2025

Hi,

It is a great sharing! I want to know what is the minimum GPU usage for the Qwen2.5-VL-7B-Instruct-GPTQ-Int4? Can I train the model with lora adapter tunning using a single A4090 GPU?

hfl-rc

Joint Laboratory of HIT and iFLYTEK Research (HFL) org Mar 14, 2025

We don't have 4090 at hand. Maybe you can just download and give it a try.
Moreover, if you have successfully run Qwen2-VL-GPTQ-int4, then you'll probably fine this model too.

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