A trained machine learning model.

interface Model {
    checkpoints?: Checkpoint[];
    defaultCheckpointId?: string;
    description?: string;
    displayName?: string;
    endpoints?: Endpoint[];
    inputTokenLimit?: number;
    labels?: Record<string, string>;
    name?: string;
    outputTokenLimit?: number;
    supportedActions?: string[];
    tunedModelInfo?: TunedModelInfo;
    version?: string;
}

Properties

checkpoints?: Checkpoint[]

The checkpoints of the model.

defaultCheckpointId?: string

The default checkpoint id of a model version.

description?: string

Description of the model.

displayName?: string

Display name of the model.

endpoints?: Endpoint[]

List of deployed models created from this base model. Note that a model could have been deployed to endpoints in different locations.

inputTokenLimit?: number

The maximum number of input tokens that the model can handle.

labels?: Record<string, string>

Labels with user-defined metadata to organize your models.

name?: string

Resource name of the model.

outputTokenLimit?: number

The maximum number of output tokens that the model can generate.

supportedActions?: string[]

List of actions that are supported by the model.

tunedModelInfo?: TunedModelInfo

Information about the tuned model from the base model.

version?: string

Version ID of the model. A new version is committed when a new model version is uploaded or trained under an existing model ID. The version ID is an auto-incrementing decimal number in string representation.