sagemaker/aws.sdk.kotlin.services.sagemaker.model/ModelSpeculativeDecodingConfig/Builder

Builder

Properties

var technique: ModelSpeculativeDecodingTechnique?

The speculative decoding technique to apply during model optimization.

var trainingDataSource: ModelSpeculativeDecodingTrainingDataSource?

The location of the training data to use for speculative decoding. The data must be formatted as ShareGPT, OpenAI Completions or OpenAI Chat Completions. The input can also be unencrypted captured data from a SageMaker endpoint as long as the endpoint uses one of the above formats.

Functions

trainingDataSource

fun trainingDataSource(block: ModelSpeculativeDecodingTrainingDataSource.Builder.() -> Unit)

construct an aws.sdk.kotlin.services.sagemaker.model.ModelSpeculativeDecodingTrainingDataSource inside the given block