assets/models/system/Mistral-7B-v0-1/spec.yaml

$schema: https://azuremlschemas.azureedge.net/latest/model.schema.json
name: mistralai-Mistral-7B-v01
path: ./
properties:
  SharedComputeCapacityEnabled: true
  SHA: 26bca36bde8333b5d7f72e9ed20ccda6a618af24
  inference-min-sku-spec: 12|1|220|64
  inference-recommended-sku: Standard_NC12s_v3, Standard_NC24s_v3, Standard_ND40rs_v2, Standard_NC24ads_A100_v4, Standard_NC48ads_A100_v4, Standard_NC96ads_A100_v4, Standard_ND96amsr_A100_v4, Standard_ND96asr_v4
  evaluation-min-sku-spec: 6|1|112|128
  evaluation-recommended-sku: Standard_NC6s_v3, Standard_NC12s_v3, Standard_NC24s_v3, Standard_NC24rs_v3, Standard_ND40rs_v2, Standard_NC48ads_A100_v4, Standard_NC96ads_A100_v4, Standard_ND96amsr_A100_v4, Standard_ND96asr_v4
  finetune-min-sku-spec: 40|2|440|128
  finetune-recommended-sku: Standard_ND40rs_v2, Standard_NC48ads_A100_v4, Standard_NC96ads_A100_v4, Standard_ND96amsr_A100_v4, Standard_ND96asr_v4
  finetuning-tasks: text-generation, text-classification
  languages: EN
tags:
  Featured: ""
  SharedComputeCapacityEnabled: ""
  hiddenlayerscanned: ""
  huggingface_model_id: mistralai/Mistral-7B-v0.1
  evaluation_compute_allow_list:
    [
      Standard_NC6s_v3,
      Standard_NC12s_v3,
      Standard_NC24s_v3,
      Standard_NC24rs_v3,
      Standard_ND40rs_v2,
      Standard_NC48ads_A100_v4,
      Standard_NC96ads_A100_v4,
      Standard_ND96amsr_A100_v4,
      Standard_ND96asr_v4,
    ]
  batch_compute_allow_list:
    [
      Standard_ND40rs_v2,
      Standard_NC24ads_A100_v4,
      Standard_NC48ads_A100_v4,
      Standard_NC96ads_A100_v4,
      Standard_ND96amsr_A100_v4,
      Standard_ND96asr_v4,
    ] 
  inference_compute_allow_list:
    [
      Standard_NC12s_v3,
      Standard_NC24s_v3,
      Standard_ND40rs_v2,
      Standard_NC24ads_A100_v4,
      Standard_NC48ads_A100_v4,
      Standard_NC96ads_A100_v4,
      Standard_ND96amsr_A100_v4,
      Standard_ND96asr_v4,
    ]    
  finetune_compute_allow_list:
    [
      Standard_ND40rs_v2,
      Standard_NC48ads_A100_v4,
      Standard_NC96ads_A100_v4,
      Standard_ND96amsr_A100_v4,
      Standard_ND96asr_v4,
    ]    
  model_specific_defaults:
    precision: "16"
    deepspeed_stage: "2"
    apply_deepspeed: "true"
    apply_ort: "true"
    apply_lora: "true"
    ignore_mismatched_sizes: "false"
  inference_supported_envs:
    - vllm
    - ds_mii
  license: apache-2.0
  task: text-generation
  author: "Mistral AI"
  benchmark: "quality"
version: 19