UNPKG

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

3 lines (2 loc) 234 B
import { ChatWrapperSettings, Tokenizer } from "../../../types.js"; export declare function extractSegmentSettingsFromTokenizerAndChatTemplate(chatTemplate: string | undefined, tokenizer?: Tokenizer): ChatWrapperSettings["segments"];