Viewing Details About a Model

After a model is created, you can view its information on the details page.

  1. Log in to the ModelArts management console. In the navigation pane on the left, choose Model Management (AI Applications). The Model Management page is displayed.

  2. Click the name of the target model. The application details page is displayed.

    On the application details page, you can view the basic information and model precision of the model, and switch tab pages to view more information.

    Table 1 Basic information about a model

    Parameter

    Description

    Name

    Name of a model

    Status

    Status of a model

    Version

    Current version of a model

    ID

    ID of a model

    Size

    Size of a model

    Runtime Environment

    Runtime environment on which the meta model depends

    Meta Model Source

    Path to the meta model

    AI Engine

    AI engine used by a model

    Deployment Type

    Types of the services that a model can be deployed

    Model Source

    Source of a model, which can be ExeML, built-in algorithm, or custom algorithm

    Inference Code

    Path to the inference code

    Description

    Click the edit button to add the description of a model.

    Model Description

    Description document added during the creation of a model

    Associated Training Job

    Associated training job if the meta model comes from a training job. Click the training job name to go to its details page.

    Table 2 Details page of a model

    Parameter

    Description

    Model Precision

    Model recall, precision, accuracy, and F1 score of a model

    Parameter Configuration

    API configuration, input parameters, and output parameters of a model

    Runtime Dependency

    Model dependency on the environment. If creating a job failed, edit the runtime dependency. After the modification is saved, the system will automatically use the original image to create the job again.

    Events

    The progress of key operations during model creation

    Events are stored for three months and will be automatically cleared then.

    For details about the event types and event information of models, see What "Are the Events and Their Types for a model?" in FAQs.

    Constraint

    Constraints on deployment, such as the API request mode, deployed system architecture, and supported acceleration card types

    Associated Services

    The list of services that a model was deployed. Click a service name to go to the service details page.