assets/models/system/qwen2.5-3b-instruct-generic-gpu/spec.yaml

$schema: https://azuremlschemas.azureedge.net/latest/model.schema.json
name: qwen2.5-3b-instruct-generic-gpu
version: 1
path: ./
tags:
  foundryLocal: ""
  license: "apache-2.0"
  licenseDescription: "This model is provided under the License Terms available at <https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE>."
  author: Microsoft
  inputModalities: "text"
  outputModalities: "text"
  task: chat-completion
  maxOutputTokens: 2048
  alias: qwen2.5-3b
type: custom_model
variantInfo:
  parents:
  - assetId: azureml://registries/azureml/models/qwen2.5-3b-instruct/versions/1
  variantMetadata:
    modelType: 'ONNX'
    quantization: ['RTN']
    device: 'gpu'
    executionProvider: 'WebGPUExecutionProvider'
    fileSizeBytes: 2695091978
    vRamFootprintBytes: 2695497086