MCPcopy Create free account
hub / github.com/SooLab/CGFormer / _batch_encode_plus

Method _batch_encode_plus

bert/tokenization_utils_base.py:1835–1862  ·  view source on GitHub ↗
(
        self,
        batch_text_or_text_pairs: Union[
            List[TextInput],
            List[TextInputPair],
            List[PreTokenizedInput],
            List[PreTokenizedInputPair],
            List[EncodedInput],
            List[EncodedInputPair],
        ],
        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,
        is_pretokenized: bool = False,
        pad_to_multiple_of: Optional[int] = None,
        return_tensors: Optional[Union[str, TensorType]] = 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_offsets_mapping: bool = False,
        return_length: bool = False,
        verbose: bool = True,
        **kwargs
    )

Source from the content-addressed store, hash-verified

1833 )
1834
1835 def _batch_encode_plus(
1836 self,
1837 batch_text_or_text_pairs: Union[
1838 List[TextInput],
1839 List[TextInputPair],
1840 List[PreTokenizedInput],
1841 List[PreTokenizedInputPair],
1842 List[EncodedInput],
1843 List[EncodedInputPair],
1844 ],
1845 add_special_tokens: bool = True,
1846 padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
1847 truncation_strategy: TruncationStrategy = TruncationStrategy.DO_NOT_TRUNCATE,
1848 max_length: Optional[int] = None,
1849 stride: int = 0,
1850 is_pretokenized: bool = False,
1851 pad_to_multiple_of: Optional[int] = None,
1852 return_tensors: Optional[Union[str, TensorType]] = None,
1853 return_token_type_ids: Optional[bool] = None,
1854 return_attention_mask: Optional[bool] = None,
1855 return_overflowing_tokens: bool = False,
1856 return_special_tokens_mask: bool = False,
1857 return_offsets_mapping: bool = False,
1858 return_length: bool = False,
1859 verbose: bool = True,
1860 **kwargs
1861 ) -> BatchEncoding:
1862 raise NotImplementedError
1863
1864 def pad(
1865 self,

Callers 1

batch_encode_plusMethod · 0.95

Calls

no outgoing calls

Tested by

no test coverage detected