Instructions to use microsoft/GUI-Actor-Verifier-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/GUI-Actor-Verifier-2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="microsoft/GUI-Actor-Verifier-2B")
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("microsoft/GUI-Actor-Verifier-2B")
model = AutoModelForImageTextToText.from_pretrained("microsoft/GUI-Actor-Verifier-2B")
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 microsoft/GUI-Actor-Verifier-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/GUI-Actor-Verifier-2B"
# 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-Verifier-2B",
		"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-Verifier-2B

SGLang

How to use microsoft/GUI-Actor-Verifier-2B 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-Verifier-2B" \
    --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-Verifier-2B",
		"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-Verifier-2B" \
        --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-Verifier-2B",
		"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-Verifier-2B with Docker Model Runner:
```
docker model run hf.co/microsoft/GUI-Actor-Verifier-2B
```

nielsr HF Staff commited on Jun 5, 2025

Commit

2c522cb

verified ·

1 Parent(s): cc3ad83

Add library name, pipeline tag, and correct links

Browse files

This PR adds the `library_name` and `pipeline_tag` metadata to the model card for improved discoverability and usability on the Hugging Face Hub. It also corrects the links to the project page and paper using the provided URLs. The `mit` license is retained from the existing model card.

Files changed (1) hide show

README.md +14 -12

README.md CHANGED Viewed

@@ -1,28 +1,30 @@
 ---
-license: mit
-datasets:
-- OS-Copilot/OS-Atlas-data
 base_model:
 - ByteDance-Seed/UI-TARS-2B-SFT
 ---
 # GUI-Actor-Verifier-2B
-This model was introduced in the paper [**GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents**](https://aka.ms/GUI-Actor).
 It is developed based on [UI-TARS-2B-SFT](https://huggingface.co/ByteDance-Seed/UI-TARS-2B-SFT) and is designed to predict the correctness of an action position given a language instruction. This model is well-suited for **GUI-Actor**, as its attention map effectively provides diverse candidates for verification with only a single inference.
-For more details on model design and evaluation, please check: [🏠 Project Page](https://aka.ms/GUI-Actor) | [💻 Github Repo](https://github.com/microsoft/GUI-Actor) | [📑 Paper](https://www.arxiv.org/pdf/2506.03143).
 | Model List                                  | Hugging Face Link                         |
 |--------------------------------------------|--------------------------------------------|
-| **GUI-Actor-7B-Qwen2-VL**                   | [🤗 Hugging Face](https://huggingface.co/microsoft/GUI-Actor-7B-Qwen2-VL)         |
-| **GUI-Actor-2B-Qwen2-VL**                   | [🤗 Hugging Face](https://huggingface.co/microsoft/GUI-Actor-2B-Qwen2-VL)         |
-| **GUI-Actor-7B-Qwen2.5-VL (coming soon)**   | [🤗 Hugging Face](https://huggingface.co/microsoft/GUI-Actor-7B-Qwen2.5-VL)       |
-| **GUI-Actor-3B-Qwen2.5-VL (coming soon)**   | [🤗 Hugging Face](https://huggingface.co/microsoft/GUI-Actor-3B-Qwen2.5-VL)       |
-| **GUI-Actor-Verifier-2B**                   | [🤗 Hugging Face](https://huggingface.co/microsoft/GUI-Actor-Verifier-2B)        |
@@ -58,8 +60,8 @@ Table 2. Main results on the ScreenSpot-Pro and ScreenSpot-v2 with **Qwen2.5-VL*
 | **_3B models:_**
 | Qwen2.5-VL-3B  | Qwen2.5-VL    | 25.9           | 80.9           |
 | Jedi-3B        | Qwen2.5-VL    | 36.1           | 88.6           |
-| GUI-Actor-3B   | Qwen2.5-VL    | 42.2       | 91.0       |
-| GUI-Actor-3B + Verifier   | Qwen2.5-VL    | **45.9**       | **92.4**       |
 ## 🚀 Usage
 The verifier takes a language instruction and an image with a red circle marking the target position as input. One example is shown below. It outputs either ‘True’ or ‘False’, and you can also use the probability of each label to score the sample.

 ---
 base_model:
 - ByteDance-Seed/UI-TARS-2B-SFT
+datasets:
+- OS-Copilot/OS-Atlas-data
+license: mit
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
 # GUI-Actor-Verifier-2B
+This model was introduced in the paper [**GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents**](https://huggingface.co/papers/2506.03143).
 It is developed based on [UI-TARS-2B-SFT](https://huggingface.co/ByteDance-Seed/UI-TARS-2B-SFT) and is designed to predict the correctness of an action position given a language instruction. This model is well-suited for **GUI-Actor**, as its attention map effectively provides diverse candidates for verification with only a single inference.
+For more details on model design and evaluation, please check: [Project Page](https://microsoft.github.io/GUI-Actor/) | [Github Repo](https://github.com/microsoft/GUI-Actor) | [Paper](https://huggingface.co/papers/2506.03143).
 | Model List                                  | Hugging Face Link                         |
 |--------------------------------------------|--------------------------------------------|
+| **GUI-Actor-7B-Qwen2-VL**                   | [Hugging Face](https://huggingface.co/microsoft/GUI-Actor-7B-Qwen2-VL)         |
+| **GUI-Actor-2B-Qwen2-VL**                   | [Hugging Face](https://huggingface.co/microsoft/GUI-Actor-2B-Qwen2-VL)         |
+| **GUI-Actor-7B-Qwen2.5-VL (coming soon)**   | [Hugging Face](https://huggingface.co/microsoft/GUI-Actor-7B-Qwen2.5-VL)       |
+| **GUI-Actor-3B-Qwen2.5-VL (coming soon)**   | [Hugging Face](https://huggingface.co/microsoft/GUI-Actor-3B-Qwen2.5-VL)       |
+| **GUI-Actor-Verifier-2B**                   | [Hugging Face](https://huggingface.co/microsoft/GUI-Actor-Verifier-2B)        |
 | **_3B models:_**
 | Qwen2.5-VL-3B  | Qwen2.5-VL    | 25.9           | 80.9           |
 | Jedi-3B        | Qwen2.5-VL    | 36.1           | 88.6           |
+| GUI-Actor-3B   | Qwen2.5-VL    | **42.2**       | **91.0**       |
+| GUI-Actor-3B + Verifier   | Qwen2.5-VL    | 45.9       | 92.4       |
 ## 🚀 Usage
 The verifier takes a language instruction and an image with a red circle marking the target position as input. One example is shown below. It outputs either ‘True’ or ‘False’, and you can also use the probability of each label to score the sample.