Instructions to use ByteDance-Seed/UI-TARS-7B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ByteDance-Seed/UI-TARS-7B-SFT 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-7B-SFT")
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-7B-SFT")
model = AutoModelForImageTextToText.from_pretrained("ByteDance-Seed/UI-TARS-7B-SFT")
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-7B-SFT 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-7B-SFT"
# 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-7B-SFT",
		"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-7B-SFT

SGLang

How to use ByteDance-Seed/UI-TARS-7B-SFT 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-7B-SFT" \
    --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-7B-SFT",
		"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-7B-SFT" \
        --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-7B-SFT",
		"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-7B-SFT with Docker Model Runner:
```
docker model run hf.co/ByteDance-Seed/UI-TARS-7B-SFT
```

add AIBOM

by RiccardoDav - opened Jun 12, 2025

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

+62

-0

Files changed (1) hide show

ByteDance-Seed_UI-TARS-7B-SFT.json +62 -0

ByteDance-Seed_UI-TARS-7B-SFT.json ADDED Viewed

	@@ -0,0 +1,62 @@

+{
+    "bomFormat": "CycloneDX",
+    "specVersion": "1.6",
+    "serialNumber": "urn:uuid:3055ead6-57c6-4f53-b237-31c297a9a0db",
+    "version": 1,
+    "metadata": {
+        "timestamp": "2025-06-05T09:41:54.385491+00:00",
+        "component": {
+            "type": "machine-learning-model",
+            "bom-ref": "ByteDance-Seed/UI-TARS-7B-SFT-2563bff1-2155-555e-9ebd-c56f1c3410c5",
+            "name": "ByteDance-Seed/UI-TARS-7B-SFT",
+            "externalReferences": [
+                {
+                    "url": "https://huggingface.co/ByteDance-Seed/UI-TARS-7B-SFT",
+                    "type": "documentation"
+                }
+            ],
+            "modelCard": {
+                "modelParameters": {
+                    "task": "image-text-to-text",
+                    "architectureFamily": "qwen2_vl",
+                    "modelArchitecture": "Qwen2VLForConditionalGeneration"
+                },
+                "properties": [
+                    {
+                        "name": "library_name",
+                        "value": "transformers"
+                    }
+                ]
+            },
+            "authors": [
+                {
+                    "name": "ByteDance-Seed"
+                }
+            ],
+            "licenses": [
+                {
+                    "license": {
+                        "id": "Apache-2.0",
+                        "url": "https://spdx.org/licenses/Apache-2.0.html"
+                    }
+                }
+            ],
+            "description": "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\u2014perception, reasoning, grounding, and memory\u2014within a single vision-language model (VLM), enabling end-to-end task automation without predefined workflows or manual rules.<!-- ![Local Image](figures/UI-TARS.png) --><p align=\"center\"><img src=\"https://github.com/bytedance/UI-TARS/blob/main/figures/UI-TARS-vs-Previous-SOTA.png?raw=true\" width=\"90%\"/><p><p align=\"center\"><img src=\"https://github.com/bytedance/UI-TARS/blob/main/figures/UI-TARS.png?raw=true\" width=\"90%\"/><p><!-- ![Local Image](figures/UI-TARS-vs-Previous-SOTA.png) -->This repository contains the model for the paper [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://huggingface.co/papers/2501.12326).Code: https://github.com/bytedance/UI-TARS",
+            "tags": [
+                "transformers",
+                "safetensors",
+                "qwen2_vl",
+                "image-text-to-text",
+                "multimodal",
+                "gui",
+                "conversational",
+                "en",
+                "arxiv:2501.12326",
+                "license:apache-2.0",
+                "text-generation-inference",
+                "endpoints_compatible",
+                "region:us"
+            ]
+        }
+    }
+}