Instructions to use ByteDance-Seed/UI-TARS-72B-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ByteDance-Seed/UI-TARS-72B-DPO with Transformers:

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

pipe = pipeline("image-text-to-text", model="ByteDance-Seed/UI-TARS-72B-DPO")
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("ByteDance-Seed/UI-TARS-72B-DPO")
model = AutoModelForImageTextToText.from_pretrained("ByteDance-Seed/UI-TARS-72B-DPO")
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 ByteDance-Seed/UI-TARS-72B-DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ByteDance-Seed/UI-TARS-72B-DPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ByteDance-Seed/UI-TARS-72B-DPO",
		"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/ByteDance-Seed/UI-TARS-72B-DPO

SGLang

How to use ByteDance-Seed/UI-TARS-72B-DPO 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 "ByteDance-Seed/UI-TARS-72B-DPO" \
    --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": "ByteDance-Seed/UI-TARS-72B-DPO",
		"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 "ByteDance-Seed/UI-TARS-72B-DPO" \
        --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": "ByteDance-Seed/UI-TARS-72B-DPO",
		"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 ByteDance-Seed/UI-TARS-72B-DPO with Docker Model Runner:
```
docker model run hf.co/ByteDance-Seed/UI-TARS-72B-DPO
```

Add link to paper

by nielsr HF Staff - opened Jan 23, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-1

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -9,7 +9,6 @@ tags:
 library_name: transformers
 ---
 # UI-TARS-72B-DPO
 [UI-TARS-2B-SFT](https://huggingface.co/bytedance-research/UI-TARS-2B-SFT) &nbsp;|&nbsp;
 [UI-TARS-2B-gguf](https://huggingface.co/bytedance-research/UI-TARS-2B-gguf) &nbsp;|&nbsp;
@@ -18,6 +17,9 @@ library_name: transformers
 [UI-TARS-7B-gguf](https://huggingface.co/bytedance-research/UI-TARS-7B-gguf) &nbsp;|&nbsp;
 [UI-TARS-72B-SFT](https://huggingface.co/bytedance-research/UI-TARS-72B-SFT) &nbsp;|&nbsp;
 [UI-TARS-72B-DPO](https://huggingface.co/bytedance-research/UI-TARS-72B-DPO)
 ## Introduction
 UI-TARS is a next-generation native GUI agent model designed to interact seamlessly with graphical user interfaces (GUIs) using human-like perception, reasoning, and action capabilities. Unlike traditional modular frameworks, UI-TARS integrates all key components—perception, reasoning, grounding, and memory—within a single vision-language model (VLM), enabling end-to-end task automation without predefined workflows or manual rules.

 library_name: transformers
 ---
 # UI-TARS-72B-DPO
 [UI-TARS-2B-SFT](https://huggingface.co/bytedance-research/UI-TARS-2B-SFT) &nbsp;|&nbsp;
 [UI-TARS-2B-gguf](https://huggingface.co/bytedance-research/UI-TARS-2B-gguf) &nbsp;|&nbsp;
 [UI-TARS-7B-gguf](https://huggingface.co/bytedance-research/UI-TARS-7B-gguf) &nbsp;|&nbsp;
 [UI-TARS-72B-SFT](https://huggingface.co/bytedance-research/UI-TARS-72B-SFT) &nbsp;|&nbsp;
 [UI-TARS-72B-DPO](https://huggingface.co/bytedance-research/UI-TARS-72B-DPO)
+This repository contains the model of the paper [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://huggingface.co/papers/2501.12326).
 ## Introduction
 UI-TARS is a next-generation native GUI agent model designed to interact seamlessly with graphical user interfaces (GUIs) using human-like perception, reasoning, and action capabilities. Unlike traditional modular frameworks, UI-TARS integrates all key components—perception, reasoning, grounding, and memory—within a single vision-language model (VLM), enabling end-to-end task automation without predefined workflows or manual rules.