llama_token_to_piece method
Token Id -> Piece. Uses the vocabulary in the provided context. Does not write null terminator to the buffer. User code is responsible to remove the leading whitespace of the first non-BOS token when decoding multiple tokens.
Implementation
int llama_token_to_piece(
ffi.Pointer<llama_model> model,
int token,
ffi.Pointer<ffi.Char> buf,
int length,
) {
return _llama_token_to_piece(
model,
token,
buf,
length,
);
}