Package com.google.genai.types
Class DistillationSpec
java.lang.Object
com.google.genai.JsonSerializable
com.google.genai.types.DistillationSpec
Distillation tuning spec for tuning.
-
Nested Class Summary
Nested ClassesModifier and TypeClassDescriptionstatic classBuilder for DistillationSpec. -
Field Summary
Fields inherited from class com.google.genai.JsonSerializable
MAX_READ_LENGTH_PROPERTY -
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionThe base teacher model that is being distilled.static DistillationSpec.Builderbuilder()Instantiates a builder for DistillationSpec.static DistillationSpecDeserializes a JSON string to a DistillationSpec object.abstract Optional<DistillationHyperParameters>Optional.Deprecated.The GCS URI of the prompt dataset to use during distillation.The student model that is being tuned, e.g., "google/gemma-2b-1.1-it".abstract DistillationSpec.BuilderCreates a builder with the same values as this instance.Deprecated.The resource name of the Tuned teacher model.Optional.Methods inherited from class com.google.genai.JsonSerializable
fromJsonNode, fromJsonString, objectMapper, setMaxReadLength, stringToJsonNode, toJson, toJsonNode, toJsonString
-
Constructor Details
-
DistillationSpec
public DistillationSpec()
-
-
Method Details
-
promptDatasetUri
The GCS URI of the prompt dataset to use during distillation. -
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
Optional. Hyperparameters for Distillation. -
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
The student model that is being tuned, e.g., "google/gemma-2b-1.1-it". Deprecated. Use base_model instead. -
trainingDatasetUri
Deprecated. Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file. -
tunedTeacherModelSource
The resource name of the Tuned teacher model. Format: `projects/{project}/locations/{location}/models/{model}`. -
validationDatasetUri
Optional. Cloud Storage path to file containing validation dataset for tuning. The dataset must be formatted as a JSONL file. -
builder
Instantiates a builder for DistillationSpec. -
toBuilder
Creates a builder with the same values as this instance. -
fromJson
Deserializes a JSON string to a DistillationSpec object.
-