Skip to main content
Every time you run a model component, ClickML saves a new version of that model. The Model Selector lets you pick which version to use downstream — useful for comparing model runs or rolling back to a previous configuration.

​
Configuration

OptionDescription
VersionThe model version number to load. Versions are created automatically on each run and numbered starting from 1.

​
Input / Output

Type
InputTrained Model
OutputTrained Model (the selected version)

​
Notes

  • If no version is specified, the most recently trained model is used.
  • Model Selector is optional. You only need it when you want to explicitly target a historical run.
  • Place it between a model component and the Inference component.
Random Forest → Model Selector → Inference → Evaluation