assets/models/system/DeepSeek-R1-Distill-Qwen-7B-cuda-gpu/spec.yaml (25 lines of code) (raw):

$schema: https://azuremlschemas.azureedge.net/latest/model.schema.json name: deepseek-r1-distill-qwen-7b-cuda-gpu version: 1 path: ./ tags: foundryLocal: "" license: "MIT" licenseDescription: "This model is provided under the License Terms available at <https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/blob/main/LICENSE>." author: Microsoft inputModalities: "text" outputModalities: "text" task: chat-completion maxOutputTokens: 2048 alias: deepseek-r1-7b type: custom_model variantInfo: parents: - assetId: azureml://registries/azureml/models/deepseek-r1-distill-qwen-7b/versions/1 variantMetadata: modelType: 'ONNX' quantization: ['RTN'] device: 'gpu' executionProvider: 'CUDAExecutionProvider' fileSizeBytes: 5096273664 vRamFootprintBytes: 5096487731