Implementation:SeldonIO Seldon core Seldon Model Load For Explainer

Field	Value
Type	External Tool Doc
Overview	Concrete CLI tool for deploying base classifier models as prerequisites for explainers in Seldon Core 2.
Domains	MLOps, Explainability
Workflow	Model_Explainability
Related Principle	SeldonIO_Seldon_core_Explainer_Base_Model_Deployment
Source	samples/models/income.yaml:L1-8, samples/models/moviesentiment.yaml:L1-8, samples/explainer-examples.md:L20-62
Last Updated	2026-02-13 00:00 GMT

Code Reference

Income Classifier Model YAML

Source: samples/models/income.yaml:L1-8

apiVersion: mlops.seldon.io/v1alpha1
kind: Model
metadata:
  name: income
spec:
  storageUri: "gs://seldon-models/scv2/samples/mlserver_1.6.0/income-sklearn"
  requirements:
    - sklearn

Movie Sentiment Classifier Model YAML

Source: samples/models/moviesentiment.yaml:L1-8

apiVersion: mlops.seldon.io/v1alpha1
kind: Model
metadata:
  name: sentiment
spec:
  storageUri: "gs://seldon-models/scv2/samples/mlserver_1.6.0/moviesentiment"
  requirements:
    - sklearn

CLI Reference

seldon model load -f <model-yaml-path>
seldon model status <model-name> -w ModelAvailable

Key Parameters

Parameter	Description	Example
-f / --file-path	Path to the Model CRD YAML file	-f samples/models/income.yaml
-w / --wait	Wait condition for readiness	-w ModelAvailable
spec.storageUri	GCS or S3 URI to the serialized model artifact	gs://seldon-models/scv2/samples/mlserver_1.6.0/income-sklearn
spec.requirements	Runtime requirements for the model	sklearn

I/O Contract

Inputs

• Model CRD YAML: A Kubernetes manifest defining the base classifier model, including storageUri and requirements

Outputs

• Base model loaded and ready for inference: The model is deployed on MLServer with the appropriate runtime (e.g., sklearn) and is accessible via the V2 inference protocol

External Dependencies

• seldon CLI
• kubectl
• Seldon scheduler
• MLServer sklearn runtime

Usage Examples

Loading the Income Classifier

# Load the income classifier model
seldon model load -f samples/models/income.yaml

# Wait for the model to be ready
seldon model status income -w ModelAvailable

Loading the Movie Sentiment Classifier

# Load the sentiment classifier model
seldon model load -f samples/models/moviesentiment.yaml

# Wait for the model to be ready
seldon model status sentiment -w ModelAvailable

Verifying the Base Model with a Test Inference

# Test the income model before deploying the explainer
seldon model infer income \
  '{"inputs": [{"name": "predict", "shape": [1, 12], "datatype": "FP32", "data": [[39,7,1,1,1,1,4,1,2174,0,40,9]]}]}'

Knowledge Sources

• Repo: SeldonIO/seldon-core
• Doc: Seldon Core 2 Documentation

Related Pages

• SeldonIO_Seldon_core_Explainer_Base_Model_Deployment - parent principle - Deploying the base classifier model that the explainer will explain.
• SeldonIO_Seldon_core_Seldon_Model_CRD_Explainer_Deploy - next step - Deploying the explainer model after the base model is ready.
• SeldonIO_Seldon_core_Seldon_Model_Status_Explainer - related - Verifying readiness of both base and explainer models.