Hi there! Are you looking for the official Deno documentation? Try docs.deno.com for all your Deno learning needs.

GoogleCloudAiplatformV1GenerationConfig

import type { GoogleCloudAiplatformV1GenerationConfig } from "https://googleapis.deno.dev/v1/aiplatform:v1.ts";

Generation config.

interface GoogleCloudAiplatformV1GenerationConfig {
candidateCount?: number;
frequencyPenalty?: number;
maxOutputTokens?: number;
presencePenalty?: number;
responseMimeType?: string;
responseStyle?:
| "RESPONSE_STYLE_UNSPECIFIED"
| "RESPONSE_STYLE_PRECISE"
| "RESPONSE_STYLE_BALANCED"
| "RESPONSE_STYLE_CREATIVE";
stopSequences?: string[];
temperature?: number;
topK?: number;
topP?: number;
}

§Properties

§
candidateCount?: number
[src]

Optional. Number of candidates to generate.

§
frequencyPenalty?: number
[src]

Optional. Frequency penalties.

§
maxOutputTokens?: number
[src]

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

§
presencePenalty?: number
[src]

Optional. Positive penalties.

§
responseMimeType?: string
[src]

Optional. Output response mimetype of the generated candidate text. Supported mimetype: - text/plain: (default) Text output. - application/json: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature.

§
responseStyle?: "RESPONSE_STYLE_UNSPECIFIED" | "RESPONSE_STYLE_PRECISE" | "RESPONSE_STYLE_BALANCED" | "RESPONSE_STYLE_CREATIVE"
[src]

Optional. Control Three levels of creativity in the model output. Default: RESPONSE_STYLE_BALANCED

§
stopSequences?: string[]
[src]

Optional. Stop sequences.

§
temperature?: number
[src]

Optional. Controls the randomness of predictions.

§
topK?: number
[src]

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

§
topP?: number
[src]

Optional. If specified, nucleus sampling will be used.