Instructions to use InfiX-ai/InfiGUI-G1-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InfiX-ai/InfiGUI-G1-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="InfiX-ai/InfiGUI-G1-7B")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("InfiX-ai/InfiGUI-G1-7B")
model = AutoModelForMultimodalLM.from_pretrained("InfiX-ai/InfiGUI-G1-7B", device_map="auto")
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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use InfiX-ai/InfiGUI-G1-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "InfiX-ai/InfiGUI-G1-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InfiX-ai/InfiGUI-G1-7B",
		"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/InfiX-ai/InfiGUI-G1-7B

SGLang

How to use InfiX-ai/InfiGUI-G1-7B 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 "InfiX-ai/InfiGUI-G1-7B" \
    --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": "InfiX-ai/InfiGUI-G1-7B",
		"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 "InfiX-ai/InfiGUI-G1-7B" \
        --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": "InfiX-ai/InfiGUI-G1-7B",
		"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 InfiX-ai/InfiGUI-G1-7B with Docker Model Runner:
```
docker model run hf.co/InfiX-ai/InfiGUI-G1-7B
```

SiriusL commited on Aug 11, 2025

Commit

f521761

verified ·

1 Parent(s): 9a420d1

Update README.md

Browse files

Files changed (1) hide show

README.md +14 -2

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ library_name: transformers
 # InfiGUI-G1-7B
-This repository contains the InfiGUI-G1-7B model from the paper **[InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization](https://github.com/InfiXAI/InfiGUI-R1)**.
 The model is based on `Qwen2.5-VL-7B-Instruct` and is fine-tuned using our proposed **Adaptive Exploration Policy Optimization (AEPO)** framework. AEPO is a novel reinforcement learning method designed to enhance the model's **semantic alignment** for GUI grounding tasks. It overcomes the exploration bottlenecks of standard RLVR methods by integrating a multi-answer generation strategy with a theoretically-grounded adaptive reward function, enabling more effective and efficient learning for complex GUI interactions.
@@ -164,12 +164,24 @@ if __name__ == "__main__":
 To reproduce the results in our paper, please refer to our repo for detailed instructions.
-For more details on the methodology and evaluation, please refer to our [paper](https://github.com/InfiXAI/InfiGUI-R1) and [repository](https://github.com/InfiXAI/InfiGUI-G1).
 ## Citation Information
 If you find this work useful, we would be grateful if you consider citing the following papers:
 ```bibtex
 @article{liu2025infigui,
   title={InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners},

 # InfiGUI-G1-7B
+This repository contains the InfiGUI-G1-7B model from the paper **[InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization](https://arxiv.org/abs/2508.05731)**.
 The model is based on `Qwen2.5-VL-7B-Instruct` and is fine-tuned using our proposed **Adaptive Exploration Policy Optimization (AEPO)** framework. AEPO is a novel reinforcement learning method designed to enhance the model's **semantic alignment** for GUI grounding tasks. It overcomes the exploration bottlenecks of standard RLVR methods by integrating a multi-answer generation strategy with a theoretically-grounded adaptive reward function, enabling more effective and efficient learning for complex GUI interactions.
 To reproduce the results in our paper, please refer to our repo for detailed instructions.
+For more details on the methodology and evaluation, please refer to our [paper](https://arxiv.org/abs/2508.05731) and [repository](https://github.com/InfiXAI/InfiGUI-G1).
 ## Citation Information
 If you find this work useful, we would be grateful if you consider citing the following papers:
+```bibtex
+@misc{liu2025infiguig1advancingguigrounding,
+      title={InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization},
+      author={Yuhang Liu and Zeyu Liu and Shuanghe Zhu and Pengxiang Li and Congkai Xie and Jiasheng Wang and Xueyu Hu and Xiaotian Han and Jianbo Yuan and Xinyao Wang and Shengyu Zhang and Hongxia Yang and Fei Wu},
+      year={2025},
+      eprint={2508.05731},
+      archivePrefix={arXiv},
+      primaryClass={cs.AI},
+      url={https://arxiv.org/abs/2508.05731},
+}
+```
 ```bibtex
 @article{liu2025infigui,
   title={InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners},