assets/models/system/deepseek-r1-distill-llama-8b-cuda-gpu/spec.yaml

$schema: https://azuremlschemas.azureedge.net/latest/model.schema.json
name: deepseek-r1-distill-llama-8b-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-Llama-8B/blob/main/LICENSE>."
  author: Microsoft
  inputModalities: "text"
  outputModalities: "text"
  task: chat-completion
  maxOutputTokens: 2048
  alias: deepseek-r1-8b
type: custom_model
variantInfo:
  parents:
  - assetId: azureml://registries/azureml/models/deepseek-r1-distill-llama-8b/versions/1
  variantMetadata:
    modelType: 'ONNX'
    quantization: ['RTN']
    device: 'gpu'
    executionProvider: 'CUDAExecutionProvider'
    fileSizeBytes: 5304284610
    vRamFootprintBytes: 5304515348