Interface GenerationConfig (0.5.0)

Configuration options for model generation and outputs.

Package

@google-cloud/vertexai

Properties

candidate_count

candidate_count?: number;

Optional. Number of candidates to generate.

max_output_tokens

max_output_tokens?: number;

Optional. The maximum number of output tokens to generate per message.

stop_sequences

stop_sequences?: string[];

Optional. Stop sequences.

temperature

temperature?: number;

Optional. Controls the randomness of predictions.

top_k

top_k?: number;

Optional. If specified, top-k sampling will be used.

top_p

top_p?: number;

Optional. If specified, nucleus sampling will be used.