Instructions to use HongxinLi/UIPro-7B_Stage2_Web with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HongxinLi/UIPro-7B_Stage2_Web with Transformers:

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

pipe = pipeline("image-text-to-text", model="HongxinLi/UIPro-7B_Stage2_Web")
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("HongxinLi/UIPro-7B_Stage2_Web")
model = AutoModelForImageTextToText.from_pretrained("HongxinLi/UIPro-7B_Stage2_Web")
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 HongxinLi/UIPro-7B_Stage2_Web with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HongxinLi/UIPro-7B_Stage2_Web"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HongxinLi/UIPro-7B_Stage2_Web",
		"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/HongxinLi/UIPro-7B_Stage2_Web

SGLang

How to use HongxinLi/UIPro-7B_Stage2_Web 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 "HongxinLi/UIPro-7B_Stage2_Web" \
    --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": "HongxinLi/UIPro-7B_Stage2_Web",
		"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 "HongxinLi/UIPro-7B_Stage2_Web" \
        --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": "HongxinLi/UIPro-7B_Stage2_Web",
		"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 HongxinLi/UIPro-7B_Stage2_Web with Docker Model Runner:
```
docker model run hf.co/HongxinLi/UIPro-7B_Stage2_Web
```

UIPro: Unleashing Superior Interaction Capability For GUI Agents

[💻Code] [🚀Quick Start] [📝Paper]

Model Details

Model Description

Developed by: Brave Group, CASIA
Model type: Vision-Language Model
Language(s) (NLP): English
License: Apache License 2.0
Finetuned from model: Qwen2-VL-7B-Instruct

Model Sources

HongxinLi/UIPro-7B_Stage2_Web is a GUI agentic model finetuned from Qwen2-VL-7B-Instruct. This model is the web-oriented embodiment of UIPro and capable of solving GUI agent tasks on web scenarios.

Repository: https://github.com/ZJULiHongxin/UIPro
Paper: https://arxiv.org/abs/2509.17328

Uses

Direct Use

First, ensure that the necessary dependencies are installed:

pip install transformers
pip install qwen-vl-utils

Inference code example:

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info

# Default: Load the model on the available device(s)
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "HongxinLi/UIPro-7B_Stage2_Mobile", torch_dtype="auto", device_map="auto"
)
processor = AutoProcessor.from_pretrained("HongxinLi/UIPro-7B_Stage2_Mobile")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "./web_6f93090a-81f6-489e-bb35-1a2838b18c01.png",
            },

            {"type": "text", "text": """Given the Web UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: {task}
Action history: {action_history}

Now, first describe the action intent and then directly plan the next action."""},
        ],
    }
]

Citation

BibTeX:

@InProceedings{Li_2025_ICCV,
    author    = {Li, Hongxin and Su, Jingran and Chen, Jingfan and Ju, Zheng and Chen, Yuntao and Li, Qing and Zhang, Zhaoxiang},
    title     = {UIPro: Unleashing Superior Interaction Capability For GUI Agents},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2025},
    pages     = {1613-1623}
}

Framework versions

PEFT 0.11.1

Downloads last month: 3

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for HongxinLi/UIPro-7B_Stage2_Web

Base model

Qwen/Qwen2-VL-7B

Finetuned

Qwen/Qwen2-VL-7B-Instruct

Finetuned

(595)

this model

Paper for HongxinLi/UIPro-7B_Stage2_Web

UIPro: Unleashing Superior Interaction Capability For GUI Agents

Paper • 2509.17328 • Published Sep 22, 2025