node-llama-cpp
Version:
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
45 lines (44 loc) • 1.29 kB
TypeScript
import { CommandModule } from "yargs";
import { BuildGpu, LlamaNuma } from "../../bindings/types.js";
import { ParsedXtcArg } from "../utils/parseXtcArg.js";
type CompleteCommand = {
modelPath?: string;
header?: string[];
gpu?: BuildGpu | "auto";
systemInfo: boolean;
text?: string;
textFile?: string;
contextSize?: number;
batchSize?: number;
flashAttention?: boolean;
swaFullCache?: boolean;
threads?: number;
temperature: number;
minP: number;
topK: number;
topP: number;
seed?: number;
xtc?: ParsedXtcArg;
gpuLayers?: number;
repeatPenalty: number;
dryRepeatPenaltyStrength?: number;
dryRepeatPenaltyBase?: number;
dryRepeatPenaltyAllowedLength?: number;
dryRepeatPenaltyLastTokens?: number;
lastTokensRepeatPenalty: number;
penalizeRepeatingNewLine: boolean;
repeatFrequencyPenalty?: number;
repeatPresencePenalty?: number;
maxTokens: number;
tokenPredictionDraftModel?: string;
tokenPredictionModelContextSize?: number;
debug: boolean;
numa?: LlamaNuma;
meter: boolean;
timing: boolean;
noMmap: boolean;
noDirectIo: boolean;
printTimings: boolean;
};
export declare const CompleteCommand: CommandModule<object, CompleteCommand>;
export {};