AIDC-AI_Ovis1.6-Gemma2-9B.json

{
    "bomFormat": "CycloneDX",
    "specVersion": "1.6",
    "serialNumber": "urn:uuid:7611ea51-f4d2-4d7d-8423-c454737b6e82",
    "version": 1,
    "metadata": {
        "timestamp": "2025-07-10T09:22:31.938007+00:00",
        "component": {
            "type": "machine-learning-model",
            "bom-ref": "AIDC-AI/Ovis1.6-Gemma2-9B-e39fac17-8b40-541a-ae36-5ba9dd911393",
            "name": "AIDC-AI/Ovis1.6-Gemma2-9B",
            "externalReferences": [
                {
                    "url": "https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B",
                    "type": "documentation"
                }
            ],
            "modelCard": {
                "modelParameters": {
                    "task": "image-text-to-text",
                    "architectureFamily": "ovis",
                    "modelArchitecture": "Ovis",
                    "datasets": [
                        {
                            "ref": "AIDC-AI/Ovis-dataset-2b0700c9-2ab5-5db9-9b2b-d9cfc06e2a69"
                        }
                    ]
                },
                "properties": [
                    {
                        "name": "library_name",
                        "value": "transformers"
                    }
                ]
            },
            "authors": [
                {
                    "name": "AIDC-AI"
                }
            ],
            "licenses": [
                {
                    "license": {
                        "id": "Apache-2.0",
                        "url": "https://spdx.org/licenses/Apache-2.0.html"
                    }
                }
            ],
            "description": "[GitHub](https://github.com/AIDC-AI/Ovis) | [Demo](https://huggingface.co/spaces/AIDC-AI/Ovis1.6-Gemma2-9B) | [Paper](https://arxiv.org/abs/2405.20797)We are excited to announce the open-sourcing of **Ovis-1.6**, our latest multi-modal large language model. Ovis is a novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.<div align=\"center\"><img src=\"https://cdn-uploads.huggingface.co/production/uploads/658a8a837959448ef5500ce5/TIlymOb86R6_Mez3bpmcB.png\" width=\"100%\" /></div>",
            "tags": [
                "transformers",
                "safetensors",
                "ovis",
                "text-generation",
                "MLLM",
                "image-text-to-text",
                "conversational",
                "custom_code",
                "en",
                "dataset:AIDC-AI/Ovis-dataset",
                "arxiv:2405.20797",
                "license:apache-2.0",
                "autotrain_compatible",
                "region:us"
            ]
        }
    },
    "components": [
        {
            "type": "data",
            "bom-ref": "AIDC-AI/Ovis-dataset-2b0700c9-2ab5-5db9-9b2b-d9cfc06e2a69",
            "name": "AIDC-AI/Ovis-dataset",
            "data": [
                {
                    "type": "dataset",
                    "bom-ref": "AIDC-AI/Ovis-dataset-2b0700c9-2ab5-5db9-9b2b-d9cfc06e2a69",
                    "name": "AIDC-AI/Ovis-dataset",
                    "contents": {
                        "url": "https://huggingface.co/datasets/AIDC-AI/Ovis-dataset",
                        "properties": [
                            {
                                "name": "task_categories",
                                "value": "visual-question-answering"
                            },
                            {
                                "name": "license",
                                "value": "cc-by-4.0"
                            }
                        ]
                    },
                    "governance": {
                        "owners": [
                            {
                                "organization": {
                                    "name": "AIDC-AI",
                                    "url": "https://huggingface.co/AIDC-AI"
                                }
                            }
                        ]
                    },
                    "description": "\n\t\n\t\t\n\t\tUsage\n\t\n\nhttps://github.com/AIDC-AI/Ovis/tree/v1.5?tab=readme-ov-file#dataset\n\n\t\n\t\t\n\t\tDescription\n\t\n\nThis dataset is a collection of multimodal datasets used for training Ovis. Ovis is a novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings. For a comprehensive introduction, please refer to the Ovis paper and the Ovis GitHub repo.\n\n\t\n\t\t\n\t\tLicense\n\t\n\nThe files laion-description-11k.json, cc12m-description-1m.json, and\u2026 See the full description on the dataset page: https://huggingface.co/datasets/AIDC-AI/Ovis-dataset."
                }
            ]
        }
    ]
}