/** * Minimal GGUF header reader — just enough to answer "what pooling does this * model declare?" without loading the model. * * Why it exists (issue #12): the native addon accepts no pooling option, so * the llama.cpp context always resolves pooling from the model's own * `.pooling_type` metadata — and when that key is missing (common in * third-party GGUF conversions), llama.cpp falls back to an arch-dependent * default that may silently mean-pool a last-token model. Degraded vectors, * no error. We can't override the pooling, but we CAN verify the file * declares what the caller expects and fail loudly at init when it doesn't. * * Parses only the metadata KV section (never tensor data), early-exits once * the interesting keys are found, and skips large values (tokenizer arrays) * without materializing them. */ declare const POOLING_TYPES: { readonly none: 0; readonly mean: 1; readonly cls: 2; readonly last: 3; readonly rank: 4; }; export type PoolingName = keyof typeof POOLING_TYPES; export declare const POOLING_NAMES: readonly PoolingName[]; export interface GgufPoolingInfo { /** `general.architecture`, when present (e.g. `qwen3`, `bert`). */ architecture?: string; /** Value of the `.pooling_type` key, when declared. */ poolingType?: number; } /** * Read `general.architecture` and the model's `.pooling_type` from a * GGUF file's metadata. Matches the pooling key by `.pooling_type` suffix so * key order relative to `general.architecture` doesn't matter. Returns what * it found; both fields are optional — absence is data, not an error. */ export declare function readGgufPooling(modelPath: string): Promise; /** * Verify a model file declares the pooling the caller expects. The addon * offers no pooling override, so a declaration that isn't in the file cannot * be satisfied — fail at init (registration time) instead of silently * producing wrong-pooling vectors. */ export declare function assertDeclaredPooling(modelPath: string, declared: PoolingName): Promise; export {}; //# sourceMappingURL=gguf.d.ts.map