Class: Aws::SageMaker::Types::ModelSpeculativeDecodingConfig

Inherits:

Struct

• Object
• Struct
• Aws::SageMaker::Types::ModelSpeculativeDecodingConfig

Includes:

Aws::Structure

Defined in:

lib/aws-sdk-sagemaker/types.rb

Overview

Settings for the model speculative decoding technique that’s applied by a model optimization job.

See Also:

• AWS API Documentation

Constant Summary

SENSITIVE =

[]

Instance Attribute Summary

• #technique ⇒ String

  The speculative decoding technique to apply during model optimization.

• #training_data_source ⇒ Types::ModelSpeculativeDecodingTrainingDataSource

  The location of the training data to use for speculative decoding.

Instance Attribute Details

#technique ⇒ String

The speculative decoding technique to apply during model optimization.

Returns:

• (String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 39946

class ModelSpeculativeDecodingConfig < Struct.new(
  :technique,
  :training_data_source)
  SENSITIVE = []
  include Aws::Structure
end

#training_data_source ⇒ Types::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.

Returns:

• (Types::ModelSpeculativeDecodingTrainingDataSource)

# File 'lib/aws-sdk-sagemaker/types.rb', line 39946

class ModelSpeculativeDecodingConfig < Struct.new(
  :technique,
  :training_data_source)
  SENSITIVE = []
  include Aws::Structure
end