Package com.google.genai.types

Class DistillationHyperParameters

java.lang.Object

com.google.genai.JsonSerializable

com.google.genai.types.DistillationHyperParameters

@InternalApi
public abstract class DistillationHyperParameters
extends JsonSerializable

Distillation hyperparameters for tuning.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	DistillationHyperParameters.Builder	Builder for DistillationHyperParameters.

Field Summary

Fields inherited from class com.google.genai.JsonSerializable

MAX_READ_LENGTH_PROPERTY

Constructor Summary

Constructors

Constructor	Description
DistillationHyperParameters()

Method Summary

Modifier and Type	Method	Description
abstract Optional<AdapterSize>	adapterSize()	The size of the adapter.
abstract Optional<Integer>	batchSize()	Batch size for tuning.
static DistillationHyperParameters.Builder	builder()	Instantiates a builder for DistillationHyperParameters.
abstract Optional<Long>	epochCount()	Number of complete passes the model makes over the entire training dataset during training.
static DistillationHyperParameters	fromJson(String jsonString)	Deserializes a JSON string to a DistillationHyperParameters object.
abstract Optional<GenerationConfig>	generationConfig()	Generation config for Distillation teacher model sampling.
abstract Optional<Float>	learningRate()	The learning rate for distillation tuning.
abstract Optional<Float>	learningRateMultiplier()	Multiplier for adjusting the default learning rate.
abstract DistillationHyperParameters.Builder	toBuilder()	Creates a builder with the same values as this instance.

Methods inherited from class com.google.genai.JsonSerializable

fromJsonNode, fromJsonString, objectMapper, setMaxReadLength, stringToJsonNode, toJson, toJsonNode, toJsonString

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

DistillationHyperParameters

public DistillationHyperParameters()

Method Details

adapterSize

public abstract Optional<AdapterSize> adapterSize()

The size of the adapter. Can be 'small', 'medium', or 'large'.

epochCount

public abstract Optional<Long> epochCount()

Number of complete passes the model makes over the entire training dataset during training.

learningRateMultiplier

public abstract Optional<Float> learningRateMultiplier()

Multiplier for adjusting the default learning rate.

generationConfig

public abstract Optional<GenerationConfig> generationConfig()

Generation config for Distillation teacher model sampling. Only the following fields are supported for distillation teacher samplings: - temperature - top_p - top_k - candidate_count - thinking_config

learningRate

public abstract Optional<Float> learningRate()

The learning rate for distillation tuning.

batchSize

public abstract Optional<Integer> batchSize()

Batch size for tuning. This feature is only available for open source models.

builder

public static DistillationHyperParameters.Builder builder()

Instantiates a builder for DistillationHyperParameters.

toBuilder

public abstract DistillationHyperParameters.Builder toBuilder()

Creates a builder with the same values as this instance.

fromJson

public static DistillationHyperParameters fromJson(String jsonString)

Deserializes a JSON string to a DistillationHyperParameters object.