{
    "bomFormat": "CycloneDX",
    "specVersion": "1.6",
    "serialNumber": "urn:uuid:4ec612d6-0e01-4883-8931-409c560fd885",
    "version": 1,
    "metadata": {
        "timestamp": "2025-07-21T08:19:51.846071+00:00",
        "component": {
            "type": "machine-learning-model",
            "bom-ref": "Xkev/Llama-3.2V-11B-cot-9618fe23-9615-538b-9533-c062d681ea6b",
            "licenses": [
                {
                    "license": {
                        "id": "Apache-2.0",
                        "url": "https://spdx.org/licenses/Apache-2.0.html"
                    }
                }
            ],
            "externalReferences": [
                {
                    "url": "https://huggingface.co/Xkev/Llama-3.2V-11B-cot",
                    "type": "documentation"
                }
            ],
            "modelCard": {
                "modelParameters": {
                    "datasets": [
                        {
                            "ref": "Xkev/LLaVA-CoT-100k-c9c723f9-0fc7-5fcc-a916-d80870eaabe0"
                        }
                    ],
                    "task": "image-text-to-text",
                    "architectureFamily": "mllama",
                    "modelArchitecture": "MllamaForConditionalGeneration"
                },
                "properties": [
                    {
                        "name": "library_name",
                        "value": "transformers"
                    },
                    {
                        "name": "base_model",
                        "value": "meta-llama/Llama-3.2-11B-Vision-Instruct"
                    }
                ]
            },
            "name": "Xkev/Llama-3.2V-11B-cot",
            "authors": [
                {
                    "name": "Xkev"
                }
            ],
            "description": "<!-- Provide a longer summary of what this model is. -->- **License:** apache-2.0- **Finetuned from model:** meta-llama/Llama-3.2-11B-Vision-Instruct",
            "tags": [
                "transformers",
                "safetensors",
                "mllama",
                "image-to-text",
                "image-text-to-text",
                "conversational",
                "en",
                "dataset:Xkev/LLaVA-CoT-100k",
                "arxiv:2411.10440",
                "base_model:meta-llama/Llama-3.2-11B-Vision-Instruct",
                "base_model:finetune:meta-llama/Llama-3.2-11B-Vision-Instruct",
                "license:apache-2.0",
                "text-generation-inference",
                "endpoints_compatible",
                "region:us"
            ]
        }
    },
    "components": [
        {
            "type": "data",
            "bom-ref": "Xkev/LLaVA-CoT-100k-c9c723f9-0fc7-5fcc-a916-d80870eaabe0",
            "name": "Xkev/LLaVA-CoT-100k",
            "data": [
                {
                    "type": "dataset",
                    "bom-ref": "Xkev/LLaVA-CoT-100k-c9c723f9-0fc7-5fcc-a916-d80870eaabe0",
                    "name": "Xkev/LLaVA-CoT-100k",
                    "contents": {
                        "url": "https://huggingface.co/datasets/Xkev/LLaVA-CoT-100k",
                        "properties": [
                            {
                                "name": "task_categories",
                                "value": "visual-question-answering"
                            },
                            {
                                "name": "language",
                                "value": "en"
                            },
                            {
                                "name": "size_categories",
                                "value": "10K<n<100K"
                            },
                            {
                                "name": "pretty_name",
                                "value": "LLaVA-CoT"
                            },
                            {
                                "name": "license",
                                "value": "apache-2.0"
                            }
                        ]
                    },
                    "description": "\n\t\n\t\t\n\t\tDataset Card for LLaVA-CoT\n\t\n\n\n\t\n\t\t\n\t\tDataset Sources\n\t\n\n\nRepository: [https://github.com/PKU-YuanGroup/LLaVA-CoT]\nPaper: [https://arxiv.org/abs/2411.10440]\n\n\n\t\n\t\t\n\t\tDataset Structure\n\t\n\nThe repository includes image.zip.part-{aa-ap}, which you need to merge manually. Use the following command to combine them:\ncat image.zip.part-* > image.zip\nunzip image.zip\n\nThe train.jsonl file contains the question-answering data in the following format:\n{\n\"id\": ID,\n\"image\": IMAGE_PATH\u2026 See the full description on the dataset page: https://huggingface.co/datasets/Xkev/LLaVA-CoT-100k.",
                    "governance": {
                        "owners": [
                            {
                                "organization": {
                                    "name": "Xkev",
                                    "url": "https://huggingface.co/Xkev"
                                }
                            }
                        ]
                    }
                }
            ]
        }
    ]
}