GuidesRecipesAPI ReferenceChangelogDiscussions
Log In

Manage model versions


Model versions represent different instances of a model. For many reasons, models change over time and a new set of complete, bundled, and tested changes represent new version. Versions can include fixes or minor updates but they can also include large changes.
When you deploy a model for the first time, a model version is created. Later on, you can deploy new model versions. All active versions can be used to run a job lifecycle.

View Model Version Details

Model details for each model version are stored in the Model Library. To view each independent version of a model, navigate to the model detail page. The default view is set to the most recent version of each model. Click the version dropdown on the top left side to view information for all previous versions of the model.


Model version details on Model Details page

Enable/Disable Model Versions

To enable or disable specific model versions, navigate to the "Operations" tab in the primary header. From there select the "Model Management" tab. The default view on this page is of all deployed and Active models. To view all Inactive models, click the dropdown on the right side and select "Inactive Models."


Active models view

To deactivate a model version, you can either use the search bar at the top of the page, or manually click through the pages to identify the specific model and version. You will then click the Action button with the three horizontal dots to the right of the model, and hit "Deactivate model." This will immediately send your model version to the "Inactivated Models" section.


Deactivating a model version

Model Metrics

To view metrics on each specific model version, in the same "Model Management" page, click the dropdown to the left of each model name. This will display how metrics for that model version including how many jobs have been run against it, amount of data processed, average latency, and number of users. You can also view the last time the model version, was used, how many processing engines it has allocated to running it, and the status of the engines.


Model Metrics for each model version