Interface GenerationConfig (0.2.1)

Configuration options for model generation and outputs {number} - [candidate_count] Number of candidates to generate. {string[]} - [stop_sequences] Stop sequences. {number} - [max_output_tokens] The maximum number of output tokens to generate per message. {number} - [temperature] Controls the randomness of predictions. {number} - [top_p] If specified, nucleus sampling will be used. {number} - [top_k] If specified, top-k sampling will be used.

Package

@google-cloud/vertexai

Properties

candidate_count

candidate_count?: number;

max_output_tokens

max_output_tokens?: number;

stop_sequences

stop_sequences?: string[];

temperature

temperature?: number;

top_k

top_k?: number;

top_p

top_p?: number;