Package com.google.genai.types
Class DistillationSamplingSpec
java.lang.Object
com.google.genai.JsonSerializable
com.google.genai.types.DistillationSamplingSpec
Spec for creating a distilled dataset in Vertex Dataset. This data type is not supported in
Gemini API.
-
Nested Class Summary
Nested ClassesModifier and TypeClassDescriptionstatic classBuilder for DistillationSamplingSpec. -
Field Summary
Fields inherited from class com.google.genai.JsonSerializable
MAX_READ_LENGTH_PROPERTY -
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionOptional.builder()Instantiates a builder for DistillationSamplingSpec.static DistillationSamplingSpecDeserializes a JSON string to a DistillationSamplingSpec object.abstract DistillationSamplingSpec.BuilderCreates a builder with the same values as this instance.Optional.Optional.Methods inherited from class com.google.genai.JsonSerializable
fromJsonNode, fromJsonString, objectMapper, setMaxReadLength, stringToJsonNode, toJson, toJsonNode, toJsonString
-
Constructor Details
-
DistillationSamplingSpec
public DistillationSamplingSpec()
-
-
Method Details
-
baseTeacherModel
Optional. 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). -
tunedTeacherModelSource
Optional. 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 distillation. The dataset must be formatted as a JSONL file. -
builder
Instantiates a builder for DistillationSamplingSpec. -
toBuilder
Creates a builder with the same values as this instance. -
fromJson
Deserializes a JSON string to a DistillationSamplingSpec object.
-