Table of Contents

Class AutoraterConfig

Namespace
GenerativeAI.Types
Assembly
GenerativeAI.dll

Autorater config used for model evaluation during tuning.

public class AutoraterConfig
Inheritance
AutoraterConfig
Inherited Members
Extension Methods

Properties

AutoraterModel

The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: projects/{project}/locations/{location}/publishers/{publisher}/models/{model} Tuned model format: projects/{project}/locations/{location}/models/{model}

[JsonPropertyName("autoraterModel")]
public string? AutoraterModel { get; set; }

Property Value

string

FlipEnabled

Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.

[JsonPropertyName("flipEnabled")]
public bool? FlipEnabled { get; set; }

Property Value

bool?

GenerationConfig

Configuration options for the autorater model generation and outputs.

[JsonPropertyName("generationConfig")]
public GenerationConfig? GenerationConfig { get; set; }

Property Value

GenerationConfig

SamplingCount

Number of samples for each instance in the dataset. If not specified, the default is 4. Minimum value is 1, maximum value is 32.

[JsonPropertyName("samplingCount")]
public int? SamplingCount { get; set; }

Property Value

int?