Constructor Detail

• Model

  Model()

Method Detail

• name

   abstract Optional<String> name()

  Resource name of the model.

• displayName

   abstract Optional<String> displayName()

  Display name of the model.

• description

   abstract Optional<String> description()

  Description of the model.

• version

   abstract Optional<String> version()

  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.

• endpoints

   abstract Optional<List<Endpoint>> endpoints()

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

• labels

   abstract Optional<Map<String, String>> labels()

  Labels with user-defined metadata to organize your models.

• tunedModelInfo

   abstract Optional<TunedModelInfo> tunedModelInfo()

  Information about the tuned model from the base model.

• inputTokenLimit

   abstract Optional<Integer> inputTokenLimit()

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

• outputTokenLimit

   abstract Optional<Integer> outputTokenLimit()

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

• supportedActions

   abstract Optional<List<String>> supportedActions()

  List of actions that are supported by the model.

• defaultCheckpointId

   abstract Optional<String> defaultCheckpointId()

  The default checkpoint id of a model version.

• checkpoints

   abstract Optional<List<Checkpoint>> checkpoints()

  The checkpoints of the model.

• temperature

   abstract Optional<Float> temperature()

  Temperature value used for sampling set when the dataset was saved. This value is used to tune the degree of randomness.

• maxTemperature

   abstract Optional<Float> maxTemperature()

  The maximum temperature value used for sampling set when the dataset was saved. This value is used to tune the degree of randomness.

• topP

   abstract Optional<Float> topP()

  Optional. Specifies the nucleus sampling threshold. The model considers only the smallest set of tokens whose cumulative probability is at least `top_p`. This helps generate more diverse and less repetitive responses. For example, a `top_p` of 0.9 means the model considers tokens until the cumulative probability of the tokens to select from reaches 0.9. It's recommended to adjust either temperature or `top_p`, but not both.

• topK

   abstract Optional<Integer> topK()

  Optional. Specifies the top-k sampling threshold. The model considers only the top k most probable tokens for the next token. This can be useful for generating more coherent and less random text. For example, a `top_k` of 40 means the model will choose the next word from the 40 most likely words.

• thinking

   abstract Optional<Boolean> thinking()

  Whether the model supports thinking features. If true, thoughts are returned only if the model supports thought and thoughts are available.

• builder

   static Model.Builder builder()

  Instantiates a builder for Model.

• toBuilder

   abstract Model.Builder toBuilder()

  Creates a builder with the same values as this instance.

• fromJson

   static Model fromJson(String jsonString)

  Deserializes a JSON string to a Model object.