assets/models/system/microsoft-phi-2/spec.yaml

$schema: https://azuremlschemas.azureedge.net/latest/model.schema.json
name: microsoft-phi-2
path: ./
properties:
  SharedComputeCapacityEnabled: true
  SHA: b10c3eba545ad279e7208ee3a5d644566f001670
  datasets: StackOverflow, Stackv1.2, CodeContests, gpt-3.5-turbo-0301
  inference-min-sku-spec: 4|1|28|64
  inference-recommended-sku: Standard_NC4as_T4_v3, Standard_NC6s_v3, Standard_NC8as_T4_v3, Standard_NC12s_v3, Standard_NC16as_T4_v3, Standard_NC24s_v3, Standard_NC64as_T4_v3, Standard_NC24ads_A100_v4, Standard_NC48ads_A100_v4, Standard_NC96ads_A100_v4, Standard_ND96asr_v4, Standard_ND96amsr_A100_v4, Standard_ND40rs_v2
  languages: en
  evaluation-min-sku-spec: 6|0|56|112
  evaluation-recommended-sku: Standard_DS5_v2, Standard_NC6s_v3, Standard_NC12s_v3, Standard_NC24s_v3, Standard_NC24rs_v3, Standard_ND40rs_v2, Standard_ND96asr_v4, Standard_ND96amsr_A100_v4
  finetuning-tasks: text-generation
  finetune-min-sku-spec: 24|1|220|64
  finetune-recommended-sku: Standard_ND40rs_v2, Standard_NC24ads_A100_v4, Standard_NC48ads_A100_v4, Standard_NC96ads_A100_v4, Standard_ND96asr_v4, Standard_ND96amsr_A100_v4
tags:
  SharedComputeCapacityEnabled: ""
  license: mit
  author: Microsoft
  task: text-generation
  hiddenlayerscanned: ""
  evaluation_compute_allow_list:
    [
      Standard_DS5_v2,
      Standard_NC6s_v3,
      Standard_NC12s_v3,
      Standard_NC24s_v3,
      Standard_NC24rs_v3,
      Standard_ND40rs_v2,
      Standard_ND96asr_v4,
      Standard_ND96amsr_A100_v4,
    ]

  finetune_compute_allow_list:
    [Standard_ND40rs_v2, Standard_NC24ads_A100_v4, Standard_NC48ads_A100_v4, Standard_NC96ads_A100_v4, Standard_ND96asr_v4, Standard_ND96amsr_A100_v4]

  inference_compute_allow_list:
    [
      Standard_NC4as_T4_v3,
      Standard_NC6s_v3,
      Standard_NC8as_T4_v3,
      Standard_NC12s_v3,
      Standard_NC16as_T4_v3,
      Standard_NC24s_v3,
      Standard_NC64as_T4_v3,
      Standard_NC24ads_A100_v4,
      Standard_NC48ads_A100_v4,
      Standard_NC96ads_A100_v4,
      Standard_ND96asr_v4,
      Standard_ND96amsr_A100_v4,
      Standard_ND40rs_v2
    ]
  inference_supported_envs:
    - vllm
  model_specific_defaults:
    apply_deepspeed: "true"
    deepspeed_stage: 2
    apply_lora: "true"
    apply_ort: "false"
    precision: 16
    max_seq_length: 2048
  benchmark: "quality"
version: 19