assets/models/system/Mixtral-8x7B-v0-1/spec.yaml

$schema: https://azuremlschemas.azureedge.net/latest/model.schema.json
name: mistralai-Mixtral-8x7B-v01
path: ./
properties:
  SharedComputeCapacityEnabled: true
  SHA: 985aa055896a8f943d4a9f2572e6ea1341823841
  inference-min-sku-spec: 40|8|672|2900
  inference-recommended-sku: Standard_ND40rs_v2, 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
  languages: EN
tags:
  Featured: ''
  SharedComputeCapacityEnabled: ''
  hiddenlayerscanned: ""
  disable-batch: 'true'
  huggingface_model_id: mistralai/Mixtral-8x7B-v0.1
  inference_compute_allow_list:
    [
      Standard_ND40rs_v2,
      Standard_ND96amsr_A100_v4,
      Standard_ND96asr_v4,
    ]
  inference_supported_envs:
    - vllm
  finetune_compute_allow_list:
    - Standard_ND40rs_v2
    - Standard_NC48ads_A100_v4
    - Standard_NC96ads_A100_v4
    - Standard_ND96asr_v4
    - Standard_ND96amsr_A100_v4
  model_specific_defaults:
    max_seq_length: 2048
    apply_lora: "true"
    apply_deepspeed: "true"
    deepspeed_stage: "3"
    precision: "16"
    ignore_mismatched_sizes: "false"
  license: apache-2.0
  task: text-generation
  author: "Mistral AI"
  benchmark: "quality"
version: 15