/**
 * import/foreign/vocab.ts — fit a ported checkpoint to a different vocabulary size.
 *
 * A ported model keeps its source tokenizer's vocabulary. To pair it with another
 * tokenizer the embedding table (tied to the LM head) must have that tokenizer's row
 * count: surplus rows are dropped, missing rows are drawn small and random so the
 * new tokens start near the embedding cloud's centre. The new rows are recorded on
 * the port as synthesised, never passed off as ported.
 */
import type { PortedCheckpoint } from "./registry.js";
export interface ResizeVocabOptions {
    /** Standard deviation of new rows. Default 0.02, the usual embedding init. */
    std?: number;
    /** Seed for the new rows, so the same resize produces the same checkpoint. Default 1. */
    seed?: number;
}
/** `ported` with an embedding of `vocabSize` rows and a model config to match. */
export declare function resizePortedVocab(ported: PortedCheckpoint, vocabSize: number, opts?: ResizeVocabOptions): PortedCheckpoint;
//# sourceMappingURL=vocab.d.ts.map