Package com.google.genai.types

Class SupervisedTuningSpec.Builder

java.lang.Object
com.google.genai.types.SupervisedTuningSpec.Builder
Enclosing class:
SupervisedTuningSpec
public abstract static class SupervisedTuningSpec.Builder extends Object
Builder for SupervisedTuningSpec.

  • Constructor Details

    • Builder

      public Builder()

  • Method Details

    • exportLastCheckpointOnly

      public abstract SupervisedTuningSpec.Builder exportLastCheckpointOnly(boolean exportLastCheckpointOnly)
      Setter for exportLastCheckpointOnly.

      exportLastCheckpointOnly: Optional. If set to true, disable intermediate checkpoints for SFT and only the last checkpoint will be exported. Otherwise, enable intermediate checkpoints for SFT. Default is false.

    • clearExportLastCheckpointOnly

      @CanIgnoreReturnValue public SupervisedTuningSpec.Builder clearExportLastCheckpointOnly()
      Clears the value of exportLastCheckpointOnly field.

    • hyperParameters

      public abstract SupervisedTuningSpec.Builder hyperParameters(SupervisedHyperParameters hyperParameters)
      Setter for hyperParameters.

      hyperParameters: Optional. Hyperparameters for SFT.

    • hyperParameters

      @CanIgnoreReturnValue public SupervisedTuningSpec.Builder hyperParameters(SupervisedHyperParameters.Builder hyperParametersBuilder)
      Setter for hyperParameters builder.

      hyperParameters: Optional. Hyperparameters for SFT.

    • clearHyperParameters

      @CanIgnoreReturnValue public SupervisedTuningSpec.Builder clearHyperParameters()
      Clears the value of hyperParameters field.

    • trainingDatasetUri

      public abstract SupervisedTuningSpec.Builder trainingDatasetUri(String trainingDatasetUri)
      Setter for trainingDatasetUri.

      trainingDatasetUri: Required. Training dataset used for tuning. The dataset can be specified as either a Cloud Storage path to a JSONL file or as the resource name of a Vertex Multimodal Dataset.

    • clearTrainingDatasetUri

      @CanIgnoreReturnValue public SupervisedTuningSpec.Builder clearTrainingDatasetUri()
      Clears the value of trainingDatasetUri field.

    • tuningMode

      public abstract SupervisedTuningSpec.Builder tuningMode(TuningMode tuningMode)
      Setter for tuningMode.

      tuningMode: Tuning mode.

    • clearTuningMode

      @CanIgnoreReturnValue public SupervisedTuningSpec.Builder clearTuningMode()
      Clears the value of tuningMode field.

    • tuningMode

      @CanIgnoreReturnValue public SupervisedTuningSpec.Builder tuningMode(TuningMode.Known knownType)
      Setter for tuningMode given a known enum.

      tuningMode: Tuning mode.

    • tuningMode

      @CanIgnoreReturnValue public SupervisedTuningSpec.Builder tuningMode(String tuningMode)
      Setter for tuningMode given a string.

      tuningMode: Tuning mode.

    • validationDatasetUri

      public abstract SupervisedTuningSpec.Builder validationDatasetUri(String validationDatasetUri)
      Setter for validationDatasetUri.

      validationDatasetUri: Optional. Validation dataset used for tuning. The dataset can be specified as either a Cloud Storage path to a JSONL file or as the resource name of a Vertex Multimodal Dataset.

    • clearValidationDatasetUri

      @CanIgnoreReturnValue public SupervisedTuningSpec.Builder clearValidationDatasetUri()
      Clears the value of validationDatasetUri field.

    • build

      public abstract SupervisedTuningSpec build()