{
    "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"
            ]
        }
    }
}