assets/models/system/DeepSeek-R1-Distill-Qwen-1.5B-cuda-gpu/spec.yaml (25 lines of code) (raw):
$schema: https://azuremlschemas.azureedge.net/latest/model.schema.json
name: deepseek-r1-distill-qwen-1.5b-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-1.5B/blob/main/LICENSE>."
author: Microsoft
inputModalities: "text"
outputModalities: "text"
task: chat-completion
maxOutputTokens: 2048
alias: deepseek-r1-1.5b
type: custom_model
variantInfo:
parents:
- assetId: azureml://registries/azureml/models/deepseek-r1-distill-qwen-1.5b/versions/1
variantMetadata:
modelType: 'ONNX'
quantization: ['RTN']
device: 'gpu'
executionProvider: 'CUDAExecutionProvider'
fileSizeBytes: 1073741824
vRamFootprintBytes: 1362861314