Method _batch_prepare_for_model

bert/tokenization_utils.py:560–621

Prepares a sequence of input id, or a pair of sequences of inputs ids so that it can be used by the model. It adds special tokens, truncates sequences if overflowing while taking into account the special tokens and manages a moving window (with user defined stride) for overflowing t

(
        self,
        batch_ids_pairs: List[Union[PreTokenizedInputPair, Tuple[List[int], None]]],
        add_special_tokens: bool = True,
        padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
        truncation_strategy: TruncationStrategy = TruncationStrategy.DO_NOT_TRUNCATE,
        max_length: Optional[int] = None,
        stride: int = 0,
        pad_to_multiple_of: Optional[int] = None,
        return_tensors: Optional[str] = None,
        return_token_type_ids: Optional[bool] = None,
        return_attention_mask: Optional[bool] = None,
        return_overflowing_tokens: bool = False,
        return_special_tokens_mask: bool = False,
        return_length: bool = False,
        verbose: bool = True,
    )

    @add_end_docstrings(ENCODE_KWARGS_DOCSTRING, ENCODE_PLUS_ADDITIONAL_KWARGS_DOCSTRING)
    def _batch_prepare_for_model(
        self,
        batch_ids_pairs: List[Union[PreTokenizedInputPair, Tuple[List[int], None]]],
        add_special_tokens: bool = True,
        padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
        truncation_strategy: TruncationStrategy = TruncationStrategy.DO_NOT_TRUNCATE,
        max_length: Optional[int] = None,
        stride: int = 0,
        pad_to_multiple_of: Optional[int] = None,
        return_tensors: Optional[str] = None,
        return_token_type_ids: Optional[bool] = None,
        return_attention_mask: Optional[bool] = None,
        return_overflowing_tokens: bool = False,
        return_special_tokens_mask: bool = False,
        return_length: bool = False,
        verbose: bool = True,
    ) -> BatchEncoding:
        """ Prepares a sequence of input id, or a pair of sequences of inputs ids so that it can be used by the model.
        It adds special tokens, truncates sequences if overflowing while taking into account the special tokens and
        manages a moving window (with user defined stride) for overflowing tokens

        Args:
            batch_ids_pairs: list of tokenized input ids or input ids pairs
        """

        batch_outputs = {}
        for first_ids, second_ids in batch_ids_pairs:
            outputs = self.prepare_for_model(
                first_ids,
                second_ids,
                add_special_tokens=add_special_tokens,
                padding=PaddingStrategy.DO_NOT_PAD.value,  # we pad in batch afterward
                truncation=truncation_strategy.value,
                max_length=max_length,
                stride=stride,
                pad_to_multiple_of=None,  # we pad in batch afterward
                return_attention_mask=False,  # we pad in batch afterward
                return_token_type_ids=return_token_type_ids,
                return_overflowing_tokens=return_overflowing_tokens,
                return_special_tokens_mask=return_special_tokens_mask,
                return_length=return_length,
                return_tensors=None,  # We convert the whole batch to tensors at the end
                prepend_batch_axis=False,
                verbose=verbose,
            )

            for key, value in outputs.items():
                if key not in batch_outputs:
                    batch_outputs[key] = []
                batch_outputs[key].append(value)

        batch_outputs = self.pad(
            batch_outputs,
            padding=padding_strategy.value,
            max_length=max_length,
            pad_to_multiple_of=pad_to_multiple_of,
            return_attention_mask=return_attention_mask,
        )