Qwen_Qwen2.5-72B-Instruct.json

{
    "bomFormat": "CycloneDX",
    "specVersion": "1.6",
    "serialNumber": "urn:uuid:cc0286ed-e90e-4bc1-8963-7fe3fc905c86",
    "version": 1,
    "metadata": {
        "timestamp": "2025-06-05T09:38:13.084216+00:00",
        "component": {
            "type": "machine-learning-model",
            "bom-ref": "Qwen/Qwen2.5-72B-Instruct-bdf82bad-49e1-5618-a932-a8d56c0d6da6",
            "name": "Qwen/Qwen2.5-72B-Instruct",
            "externalReferences": [
                {
                    "url": "https://huggingface.co/Qwen/Qwen2.5-72B-Instruct",
                    "type": "documentation"
                }
            ],
            "modelCard": {
                "modelParameters": {
                    "task": "text-generation",
                    "architectureFamily": "qwen2",
                    "modelArchitecture": "Qwen2ForCausalLM"
                },
                "properties": [
                    {
                        "name": "library_name",
                        "value": "transformers"
                    },
                    {
                        "name": "base_model",
                        "value": "Qwen/Qwen2.5-72B"
                    }
                ]
            },
            "authors": [
                {
                    "name": "Qwen"
                }
            ],
            "licenses": [
                {
                    "license": {
                        "name": "qwen",
                        "url": "https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE"
                    }
                }
            ],
            "description": "Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:- Significantly **more knowledge** and has greatly improved capabilities in **coding** and **mathematics**, thanks to our specialized expert models in these domains.- Significant improvements in **instruction following**, **generating long texts** (over 8K tokens), **understanding structured data** (e.g, tables), and **generating structured outputs** especially JSON. **More resilient to the diversity of system prompts**, enhancing role-play implementation and condition-setting for chatbots.- **Long-context Support** up to 128K tokens and can generate up to 8K tokens.- **Multilingual support** for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.**This repo contains the instruction-tuned 72B Qwen2.5 model**, which has the following features:- Type: Causal Language Models- Training Stage: Pretraining & Post-training- Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias- Number of Parameters: 72.7B- Number of Paramaters (Non-Embedding): 70.0B- Number of Layers: 80- Number of Attention Heads (GQA): 64 for Q and 8 for KV- Context Length: Full 131,072 tokens and generation 8192 tokens- Please refer to [this section](#processing-long-texts) for detailed instructions on how to deploy Qwen2.5 for handling long texts.For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/).",
            "tags": [
                "transformers",
                "safetensors",
                "qwen2",
                "text-generation",
                "chat",
                "conversational",
                "en",
                "arxiv:2309.00071",
                "arxiv:2407.10671",
                "base_model:Qwen/Qwen2.5-72B",
                "base_model:finetune:Qwen/Qwen2.5-72B",
                "license:other",
                "autotrain_compatible",
                "text-generation-inference",
                "endpoints_compatible",
                "region:us"
            ]
        }
    }
}