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

Libraries

How to use microsoft/GUI-Actor-7B-Qwen2-VL with Transformers:

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

pipe = pipeline("image-text-to-text", model="microsoft/GUI-Actor-7B-Qwen2-VL")
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, Qwen2VLForConditionalGenerationWithPointer

processor = AutoProcessor.from_pretrained("microsoft/GUI-Actor-7B-Qwen2-VL")
model = Qwen2VLForConditionalGenerationWithPointer.from_pretrained("microsoft/GUI-Actor-7B-Qwen2-VL")
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 microsoft/GUI-Actor-7B-Qwen2-VL with vLLM:

Install from pip and serve model

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

SGLang

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

qianhuiwu commited on Jun 3, 2025

Commit

ae7947f

verified ·

1 Parent(s): 34e15c4

Update example code.

Browse files

Files changed (1) hide show

README.md +7 -4

README.md CHANGED Viewed

@@ -60,7 +60,7 @@ from qwen_vl_utils import process_vision_info
 from datasets import load_dataset
 from transformers import Qwen2VLProcessor
 from gui_actor.constants import chat_template
-from gui_actor.modeling import Qwen2VLForConditionalGenerationWithActionHead
 from gui_actor.inference import inference
@@ -68,7 +68,7 @@ from gui_actor.inference import inference
 model_name_or_path = "microsoft/GUI-Actor-7B-Qwen2-VL"
 data_processor = Qwen2VLProcessor.from_pretrained(model_name_or_path)
 tokenizer = data_processor.tokenizer
-model = Qwen2VLForConditionalGenerationWithActionHead.from_pretrained(
     model_name_or_path,
     torch_dtype=torch.bfloat16,
     device_map="cuda:0",
@@ -78,6 +78,9 @@ model = Qwen2VLForConditionalGenerationWithActionHead.from_pretrained(
 # prepare example
 dataset = load_dataset("rootsautomation/ScreenSpot")["test"]
 example = dataset[0]
 conversation = [
     {
         "role": "system",
@@ -105,9 +108,9 @@ conversation = [
 ]
 # inference
-pred = inference(conversation, model, tokenizer, data_processor, logits_processor=logits_processor_actor, use_placeholder=True, topk=3)
 px, py = pred["topk_points"][0]
-print(f"Click point: [{px}, {py}]")
 ```
 ## Citation

 from datasets import load_dataset
 from transformers import Qwen2VLProcessor
 from gui_actor.constants import chat_template
+from gui_actor.modeling import Qwen2VLForConditionalGenerationWithPointer
 from gui_actor.inference import inference
 model_name_or_path = "microsoft/GUI-Actor-7B-Qwen2-VL"
 data_processor = Qwen2VLProcessor.from_pretrained(model_name_or_path)
 tokenizer = data_processor.tokenizer
+model = Qwen2VLForConditionalGenerationWithPointer.from_pretrained(
     model_name_or_path,
     torch_dtype=torch.bfloat16,
     device_map="cuda:0",
 # prepare example
 dataset = load_dataset("rootsautomation/ScreenSpot")["test"]
 example = dataset[0]
+print(f"Intruction: {example['instruction']}")
+print(f"ground-truth action region (x1, y1, x2, y2): {[round(i, 2) for i in example['bbox']]}")
 conversation = [
     {
         "role": "system",
 ]
 # inference
+pred = inference(conversation, model, tokenizer, data_processor, use_placeholder=True, topk=3)
 px, py = pred["topk_points"][0]
+print(f"Predicted click point: [{round(px, 2)}, {round(py, 2)}]")
 ```
 ## Citation