Instructions to use Qiuchen-Wang/Qwen2.5-VL-7B-VRAG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qiuchen-Wang/Qwen2.5-VL-7B-VRAG with Transformers:

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

pipe = pipeline("image-text-to-text", model="Qiuchen-Wang/Qwen2.5-VL-7B-VRAG")
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("Qiuchen-Wang/Qwen2.5-VL-7B-VRAG")
model = AutoModelForImageTextToText.from_pretrained("Qiuchen-Wang/Qwen2.5-VL-7B-VRAG")
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 Qiuchen-Wang/Qwen2.5-VL-7B-VRAG with vLLM:

Install from pip and serve model

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

SGLang

How to use Qiuchen-Wang/Qwen2.5-VL-7B-VRAG 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 "Qiuchen-Wang/Qwen2.5-VL-7B-VRAG" \
    --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": "Qiuchen-Wang/Qwen2.5-VL-7B-VRAG",
		"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 "Qiuchen-Wang/Qwen2.5-VL-7B-VRAG" \
        --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": "Qiuchen-Wang/Qwen2.5-VL-7B-VRAG",
		"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 Qiuchen-Wang/Qwen2.5-VL-7B-VRAG with Docker Model Runner:
```
docker model run hf.co/Qiuchen-Wang/Qwen2.5-VL-7B-VRAG
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Arxiv: https://arxiv.org/abs/2505.22019

Github: https://github.com/Alibaba-NLP/VRAG

🎉 The training code and demo will be released.

✨ Model Description

VRAG is a Retrieval-Augmented Generation (RAG) model specifically designed for handling visually rich information. It integrates visual perception capabilities and is optimized via a reinforcement learning (RL) framework to significantly enhance the understanding and reasoning of visual content. The model can interact with search engines to efficiently retrieve relevant images and documents and generate accurate answers.

VRAG enables VLMs to progressively gather information from a coarse-grained to a fine-grained perspective. It is a purely visual RAG agent. VRAG-RL is a novel reinforcement learning framework tailored for training VLMs to effectively reason, retrieve, and understand visually rich information.

💻 Intended Use

Visual Document Question Answering: Extracting information from slides, reports, and other documents to answer questions.
Multimodal Information Retrieval: Searching for relevant images and text within large-scale visual document collections.
Chart and Layout Understanding: Analyzing charts, tables, and layout structures to extract key information.

🤔 Key Features

Visual Perception: Equipped with a visual perception action space, the model can focus on information-dense regions of images and acquire information from coarse to fine levels. Enhanced Retrieval: Optimized retrieval efficiency through a fine-grained reward function, ensuring the model quickly retrieves relevant images and documents. Multi-turn Reasoning: Supports multi-turn interactions, allowing the model to build a high-quality context through multiple interactions with search engines.