U
    &ºcá  ã                   @   s¤   d Z ddlZddlmZmZ e e¡ZddiZdddd	d
dddœiZ	dddddddœZ
ddiddiddiddiddiddidœZG dd„ deƒZG dd„ deƒZdS )z$Tokenization classes for DistilBERT.é    Né   )ÚBertTokenizerÚBertTokenizerFastZ
vocab_filez	vocab.txtzOhttps://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-vocab.txtzPhttps://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txtzMhttps://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-vocab.txtzNhttps://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-vocab.txtzZhttps://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-german-cased-vocab.txtzZhttps://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased-vocab.txt)zdistilbert-base-uncasedz'distilbert-base-uncased-distilled-squadzdistilbert-base-casedz%distilbert-base-cased-distilled-squadzdistilbert-base-german-casedz"distilbert-base-multilingual-casedi   Zdo_lower_caseTFc                   @   s&   e Zd ZdZeZeZeZ	e
ZdgZdS )ÚDistilBertTokenizeraW  
    Constructs a  DistilBertTokenizer.

    :class:`~transformers.DistilBertTokenizer is identical to :class:`~transformers.BertTokenizer` and runs end-to-end
    tokenization: punctuation splitting + wordpiece.

    Refer to superclass :class:`~transformers.BertTokenizer` for usage examples and documentation concerning
    parameters.
    Úattention_maskN©Ú__name__Ú
__module__Ú__qualname__Ú__doc__ÚVOCAB_FILES_NAMESZvocab_files_namesÚPRETRAINED_VOCAB_FILES_MAPZpretrained_vocab_files_mapÚ&PRETRAINED_POSITIONAL_EMBEDDINGS_SIZESZmax_model_input_sizesÚPRETRAINED_INIT_CONFIGURATIONZpretrained_init_configurationZmodel_input_names© r   r   úH/tmp/pip-unpacked-wheel-ymerj3tt/transformers/tokenization_distilbert.pyr   :   s   
r   c                   @   s&   e Zd ZdZeZeZeZ	e
ZdgZdS )ÚDistilBertTokenizerFastaš  
    Constructs a  "Fast" DistilBertTokenizer (backed by HuggingFace's `tokenizers` library).

    :class:`~transformers.DistilBertTokenizerFast` is identical to :class:`~transformers.BertTokenizerFast` and runs end-to-end
    tokenization: punctuation splitting + wordpiece.

    Refer to superclass :class:`~transformers.BertTokenizerFast` for usage examples and documentation concerning
    parameters.
    r   Nr   r   r   r   r   r   L   s   
r   )r   ÚloggingZtokenization_bertr   r   Ú	getLoggerr   Úloggerr   r   r   r   r   r   r   r   r   r   Ú<module>   s:   
úÿúú
