Class LLMObsCustomEvalConfigInferenceParams

LLM inference parameters for a custom evaluator.

Hierarchy

  • LLMObsCustomEvalConfigInferenceParams

Constructors

constructor

Properties

additionalProperties? frequencyPenalty? maxTokens? presencePenalty? temperature? topK? topP?

Constructors

constructor

Properties

Optional additionalProperties

additionalProperties?: {
    [key: string]: any;
}

A container for additional, undeclared properties. This is a holder for any undeclared properties as specified with the 'additionalProperties' keyword in the OAS document.

Type declaration

  • [key: string]: any

Optional frequencyPenalty

frequencyPenalty?: number

Frequency penalty to reduce repetition.

Optional maxTokens

maxTokens?: number

Maximum number of tokens to generate.

Optional presencePenalty

presencePenalty?: number

Presence penalty to reduce repetition.

Optional temperature

temperature?: number

Sampling temperature for the LLM.

Optional topK

topK?: number

Top-k sampling parameter.

Optional topP

topP?: number

Top-p (nucleus) sampling parameter.

Settings

Member Visibility

Theme

Generated using TypeDoc