Qwen_Qwen3-4B.json

{
    "bomFormat": "CycloneDX",
    "specVersion": "1.6",
    "serialNumber": "urn:uuid:f24b7da0-02aa-40b9-97d8-8c76756a806e",
    "version": 1,
    "metadata": {
        "timestamp": "2025-06-05T09:37:34.037173+00:00",
        "component": {
            "type": "machine-learning-model",
            "bom-ref": "Qwen/Qwen3-4B-d504bcdf-8093-598c-937c-206e9c62b7df",
            "name": "Qwen/Qwen3-4B",
            "externalReferences": [
                {
                    "url": "https://huggingface.co/Qwen/Qwen3-4B",
                    "type": "documentation"
                }
            ],
            "modelCard": {
                "modelParameters": {
                    "task": "text-generation",
                    "architectureFamily": "qwen3",
                    "modelArchitecture": "Qwen3ForCausalLM"
                },
                "properties": [
                    {
                        "name": "library_name",
                        "value": "transformers"
                    },
                    {
                        "name": "base_model",
                        "value": "Qwen/Qwen3-4B-Base"
                    }
                ]
            },
            "authors": [
                {
                    "name": "Qwen"
                }
            ],
            "licenses": [
                {
                    "license": {
                        "id": "Apache-2.0",
                        "url": "https://spdx.org/licenses/Apache-2.0.html"
                    }
                }
            ],
            "description": "**Qwen3-4B** has the following features:- Type: Causal Language Models- Training Stage: Pretraining & Post-training- Number of Parameters: 4.0B- Number of Paramaters (Non-Embedding): 3.6B- Number of Layers: 36- Number of Attention Heads (GQA): 32 for Q and 8 for KV- Context Length: 32,768 natively and [131,072 tokens with YaRN](#processing-long-texts).For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).> [!TIP]> If you encounter significant endless repetitions, please refer to the [Best Practices](#best-practices) section for optimal sampling parameters, and set the ``presence_penalty`` to 1.5.",
            "tags": [
                "transformers",
                "safetensors",
                "qwen3",
                "text-generation",
                "conversational",
                "arxiv:2309.00071",
                "arxiv:2505.09388",
                "base_model:Qwen/Qwen3-4B-Base",
                "base_model:finetune:Qwen/Qwen3-4B-Base",
                "license:apache-2.0",
                "autotrain_compatible",
                "text-generation-inference",
                "endpoints_compatible",
                "region:us"
            ]
        }
    }
}