Method eval_sequence_in_chunks

Evaluates the model for a sequence of tokens using `eval_sequence`, splitting a potentially long sequence into fixed-length chunks. This function is useful for processing complete prompts and user input in chat & role-playing use-cases. It is recommended to use this function

(
            self,
            tokens: List[int],
            state_in: Optional[NumpyArrayOrPyTorchTensor],
            state_out: Optional[NumpyArrayOrPyTorchTensor] = None,
            logits_out: Optional[NumpyArrayOrPyTorchTensor] = None,
            chunk_size: int = 16,
            use_numpy: bool = False
    )