Creating a Model Deployment with a Burstable Instance

Follow these steps to create a model deployment with a burstable instance.

• Console
• CLI
• API

• 1. From the model deployments page, select Create model deployment. If you need help finding the list of model deployments, see Listing Model Deployments.
  2. Follow the steps in Creating a Model Deployment to configure the model deployment.
  3. Under Select compute, select Change shape.
  4. Select Burstable.
  5. (Optional) In Burstable utilization per OCPU, select the baseline OCPU utilization percentage.
     This value is the percentage of OCPU you expect to use most often.

     Note
     
     For model deployments, only the value of 50% is supported.
  6. Select Select Shape.
  7. Select Create.

• Use the oci data-science model-deployment update command and required parameters to create a model deployment:

  Command

  CopyTry It

  oci data-science model-deployment create --required-param-name variable-name ... [OPTIONS]

  For example, create a deployment with:

  oci data-science model-deployment create \
  --compartment-id <MODEL_DEPLOYMENT_COMPARTMENT_OCID> \
  --model-deployment-configuration-details file://<MODEL_DEPLOYMENT_CONFIGURATION_FILE> \
  --project-id <PROJECT_OCID> \
  --display-name <MODEL_DEPLOYMENT_NAME>

  Use this model deployment JSON configuration file with this example:

  {
    "modelDeploymentConfigurationDetails": {
      "deploymentType": "SINGLE_MODEL",
      "modelConfigurationDetails": {
        "modelId": "ocid1.datasciencemodel.oc1.iad........",
        "instanceConfiguration": {
          "instanceShapeName": "VM.Standard.E4.Flex",
          "modelDeploymentInstanceShapeConfigDetails": {
            "ocpus": 1,
            "memoryInGBs": 16,
            "cpuBaseline": "BASELINE_1_2"
          }
        },
        "scalingPolicy": {
          "policyType": "FIXED_SIZE",
          "instanceCount": 1
        },
        "bandwidthMbps": 10
      },
      "environmentConfigurationDetails" : {
        "environmentConfigurationType": "OCIR_CONTAINER",
        "image": "iad.ocir.io/testtenancy/image_name:1.0.0",
        "entrypoint": [
          "python",
          "/opt/entrypoint.py"
        ],
        "serverPort": "5000",
        "healthCheckPort": "5000"
      },
      "streamConfigurationDetails": {
        "inputStreamIds": null,
        "outputStreamIds": null
      }
    }
  }

  For a complete list of parameters and values for CLI commands, see the CLI Command Reference.

• Use the CreateModelDeployment operation to create a model deployment.

  For example:

  endpoint = (
      "https://datascience.eu-milan-1.oci.oraclecloud.com/20190101/modelDeployments/"
  )
   
  config = oci.config.from_file(profile_name="OC1")
  config["region"] = "us-ashburn-1"
  token_file = config.get("security_token_file", None)
  signer = None
  if token_file:
      with open(token_file, "r", encoding="UTF-8") as file:
          token = file.read()
      private_key = oci.signer.load_private_key_from_file(config.get("key_file", ""))
      signer = oci.auth.signers.SecurityTokenSigner(token, private_key)
   
  model_deployment_details_payload = {
      "projectId": "ocid1.datascienceproject.oc1.eu-milan-1.amaaaaaabbbcccccc",
      "modelDeploymentConfigurationDetails": {
          "deploymentType": "SINGLE_MODEL",
          "modelConfigurationDetails": {
              "modelId": "ocid1.datasciencemodel.oc1.iad.amaaaaaav66vvniatytp7xjhid3inftgo52j55ozlm7hzglvvqni5wxi3bja",
              "scalingPolicy": {
                  "instanceCount": 1,
                  "policyType": "FIXED_SIZE"
              },
          "instanceConfiguration": {
              "instanceShapeName": "VM.Standard.E4.Flex",
              "modelDeploymentInstanceShapeConfigDetails": {
                  "ocpus": 1,
                  "memoryInGBs": 8,
                  "cpuBaseline": "BASELINE_1_2"
          }
        }
      },
      "streamConfigurationDetails": null
    },
          "streamConfigurationDetails": None,
          "environmentConfigurationDetails": None,
      },
      "deploymentMode": "HTTPS_ONLY",
      "displayName": "MD With Burstable VM",
      "compartmentId": "ocid1.compartment.oc1..aaaaaaaabcccccccc",
  }
   
  create_response = requests.post(
      endpoint, auth=signer, json=model_deployment_details_payload
  )
  print(create_response.text)