Method __call__

llama_cpp/llama.py:2498–2505

(
        self, input_ids: npt.NDArray[np.intc], scores: npt.NDArray[np.single]
    )

        self.prompt_tokens = None

    def __call__(
        self, input_ids: npt.NDArray[np.intc], scores: npt.NDArray[np.single]
    ) -> npt.NDArray[np.single]:
        if self.prompt_tokens is None:
            self.prompt_tokens = len(input_ids)
        if len(input_ids) - self.prompt_tokens < self.min_tokens:
            scores[self.token_eos] = -np.inf
        return scores