tjdZddlmZmZmZmZmZddlmZddl m Z ddl m Z e j eZddiZgd ZGd d e Zd gZd S) z*Tokenization class for Funnel Transformer.) Tokenizerdecoders normalizerspre_tokenizers processors) WordPiece)TokenizersBackend)logging vocab_filez vocab.txt) smallz small-basemediumz medium-base intermediatezintermediate-baselargez large-basexlargez xlarge-baseceZdZUdZeZeZdZe e d< dde e e e fzdzde de de de de de de de de de de dzde ffd ZxZS)FunnelTokenizeraf Construct a Funnel Transformer tokenizer (backed by HuggingFace's tokenizers library). Based on WordPiece. This tokenizer inherits from [`TokenizersBackend`] which contains most of the main methods. Users should refer to this superclass for more information regarding those methods. Args: vocab_file (`str`): File containing the vocabulary. do_lower_case (`bool`, *optional*, defaults to `True`): Whether or not to lowercase the input when tokenizing. unk_token (`str`, *optional*, defaults to `""`): The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead. sep_token (`str`, *optional*, defaults to `""`): The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for sequence classification or for a text and a question for question answering. It is also used as the last token of a sequence built with special tokens. pad_token (`str`, *optional*, defaults to `""`): The token used for padding, for example when batching sequences of different lengths. cls_token (`str`, *optional*, defaults to `""`): The classifier token which is used when doing sequence classification (classification of the whole sequence instead of per-token classification). It is the first token of the sequence when built with special tokens. mask_token (`str`, *optional*, defaults to `""`): The token used for masking values. This is the token used when training this model with masked language modeling. This is the token which the model will try to predict. clean_text (`bool`, *optional*, defaults to `True`): Whether or not to clean the text before tokenization by removing any control characters and replacing all whitespaces by the classic one. tokenize_chinese_chars (`bool`, *optional*, defaults to `True`): Whether or not to tokenize Chinese characters. This should likely be deactivated for Japanese (see [this issue](https://github.com/huggingface/transformers/issues/328)). bos_token (`str`, `optional`, defaults to `""`): The beginning of sentence token. eos_token (`str`, `optional`, defaults to `""`): The end of sentence token. strip_accents (`bool`, *optional*): Whether or not to strip all accents. If this option is not specified, then it will be determined by the value for `lowercase` (as in the original BERT). wordpieces_prefix (`str`, *optional*, defaults to `"##"`): The prefix for subwords. vocab (`str` or `dict[str, int]`, *optional*): Custom vocabulary dictionary. cls_token_type_idNT##vocab do_lower_case unk_token sep_token pad_token cls_token mask_token bos_token eos_token clean_texttokenize_chinese_chars strip_accentswordpieces_prefixc \||_| |_| |_| |_| |_||njt |dt |dt |dt |dt |dt |dt | di|_tt|jt ||_ tj | | | | |j _ tj|j _t!j| |j _t%jd|||||||| | | | | d |t)j|d |d |d |d|dt ||jft ||jfg|j _dS)Nrrr )r )r'handle_chinese_charsr) lowercase)prefix) rr r!r"r#r$r%r&r'r(r)r*z:2 $A:0 z:0z:0 $B:1 z:1)singlepairspecial_tokens)rr(r)r'r*str_vocabrr _tokenizerrBertNormalizer normalizerrBertPreTokenizer pre_tokenizerrdecodersuper__init__rTemplateProcessing cls_token_id sep_token_idpost_processor)selfrrr r!r"r#r$r%r&r'r(r)r*kwargs __class__s l/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/funnel/tokenization_funnel.pyr@zFunnelTokenizer.__init__[s"+&<#*$!2  EIIIIJII $IdkS^^$T$T$TUU%0%?!!7'# & & & " )7(G(I(I%"*"4r^s10SSSSSSSSSSSSSS''''''>>>>>>  H % %!;/    x x x x x 'x x x v  rI