Package com.google.genai.types

Class DistillationSpec.Builder

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

  • Constructor Details

    • Builder

      public Builder()

  • Method Details

    • baseTeacherModel

      public abstract DistillationSpec.Builder baseTeacherModel(String baseTeacherModel)
      Setter for baseTeacherModel.

      baseTeacherModel: The base teacher model that is being distilled. See [Supported models](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/tuning#supported_models).

    • hyperParameters

      public abstract DistillationSpec.Builder hyperParameters(DistillationHyperParameters hyperParameters)
      Setter for hyperParameters.

      hyperParameters: Optional. Hyperparameters for Distillation.

    • hyperParameters

      public DistillationSpec.Builder hyperParameters(DistillationHyperParameters.Builder hyperParametersBuilder)
      Setter for hyperParameters builder.

      hyperParameters: Optional. Hyperparameters for Distillation.

    • pipelineRootDirectory

      public abstract DistillationSpec.Builder pipelineRootDirectory(String pipelineRootDirectory)
      Setter for pipelineRootDirectory.

      pipelineRootDirectory: Deprecated. A path in a Cloud Storage bucket, which will be treated as the root output directory of the distillation pipeline. It is used by the system to generate the paths of output artifacts.

    • studentModel

      public abstract DistillationSpec.Builder studentModel(String studentModel)
      Setter for studentModel.

      studentModel: The student model that is being tuned, e.g., "google/gemma-2b-1.1-it". Deprecated. Use base_model instead.

    • trainingDatasetUri

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

      trainingDatasetUri: Deprecated. Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file.

    • tunedTeacherModelSource

      public abstract DistillationSpec.Builder tunedTeacherModelSource(String tunedTeacherModelSource)
      Setter for tunedTeacherModelSource.

      tunedTeacherModelSource: The resource name of the Tuned teacher model. Format: `projects/{project}/locations/{location}/models/{model}`.

    • validationDatasetUri

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

      validationDatasetUri: Optional. Cloud Storage path to file containing validation dataset for tuning. The dataset must be formatted as a JSONL file.

    • build

      public abstract DistillationSpec build()