sg~dZddlZddlmZddlmZmZmZddlm Z ddl m Z ddl m Z mZe rd d lmZndZej"eZd d d ZdZGdde Zy)z$Tokenization classes for FNet model.N)copyfile)ListOptionalTuple) AddedToken)PreTrainedTokenizerFast)is_sentencepiece_availablelogging) FNetTokenizerz spiece.modelztokenizer.json) vocab_filetokenizer_fileu▁ceZdZdZeZddgZeZ dfd Z e de fdZ dde edee ede efd Z dde edee ede efd Zdd ed eedeefd ZxZS)FNetTokenizerFastaR Construct a "fast" FNetTokenizer (backed by HuggingFace's *tokenizers* library). Adapted from [`AlbertTokenizerFast`]. Based on [Unigram](https://huggingface.co/docs/tokenizers/python/latest/components.html?highlight=unigram#models). This tokenizer inherits from [`PreTrainedTokenizerFast`] which contains most of the main methods. Users should refer to this superclass for more information regarding those methods Args: vocab_file (`str`): [SentencePiece](https://github.com/google/sentencepiece) file (generally has a *.spm* extension) that contains the vocabulary necessary to instantiate a tokenizer. do_lower_case (`bool`, *optional*, defaults to `False`): Whether or not to lowercase the input when tokenizing. remove_space (`bool`, *optional*, defaults to `True`): Whether or not to strip the text when tokenizing (removing excess spaces before and after the string). keep_accents (`bool`, *optional*, defaults to `True`): Whether or not to keep accents 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 `"[SEP]"`): 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 `"[CLS]"`): 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 `"[MASK]"`): 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. input_idstoken_type_idsc 2t| trt| ddn| } t| trt| ddn| } t|trt|ddn|}t ||f|||||||| | d | ||_||_||_||_y)NTF)lstriprstrip) r do_lower_case remove_space keep_accents unk_token sep_token pad_token cls_token mask_token) isinstancestrrsuper__init__rrrr) selfrrrrrrrrrrkwargs __class__s b/var/www/html/venv/lib/python3.12/site-packages/transformers/models/fnet/tokenization_fnet_fast.pyr"zFNetTokenizerFast.__init__Ms KUU_adJeZ 4Fku IST]_bIcJyuEir IST]_bIcJyuEir    )'%%!  +(($returncp|jr)tjj|jSdS)NF)rospathisfile)r#s r&can_save_slow_tokenizerz)FNetTokenizerFast.can_save_slow_tokenizerts$26//rww~~doo.LuLr' token_ids_0 token_ids_1cf|jg}|jg}|||z|zS||z|z|z|zS)a Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. An FNet sequence has the following format: - single sequence: `[CLS] X [SEP]` - pair of sequences: `[CLS] A [SEP] B [SEP]` Args: token_ids_0 (`List[int]`): List of IDs to which the special tokens will be added token_ids_1 (`List[int]`, *optional*): Optional second list of IDs for sequence pairs. Returns: `List[int]`: list of [input IDs](../glossary#input-ids) with the appropriate special tokens. ) sep_token_id cls_token_idr#r.r/sepclss r& build_inputs_with_special_tokensz2FNetTokenizerFast.build_inputs_with_special_tokensxsP&  !  !  $s* *[ 3&4s::r'c|jg}|jg}|t||z|zdgzSt||z|zdgzt||zdgzzS)a Creates a mask from the two sequences passed to be used in a sequence-pair classification task. An FNet sequence pair mask has the following format: ``` 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 | first sequence | second sequence | ``` if token_ids_1 is None, only returns the first portion of the mask (0s). Args: token_ids_0 (`List[int]`): List of ids. token_ids_1 (`List[int]`, *optional*): Optional second list of IDs for sequence pairs. Returns: `List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s). rr )r1r2lenr3s r&$create_token_type_ids_from_sequencesz6FNetTokenizerFast.create_token_type_ids_from_sequencesst.  !  !  s[(3./1#5 53$s*+qc1C c8I4JaS4PPPr'save_directoryfilename_prefixctjj|stj d|dytjj ||r|dzndt dz}tjj|jtjj|k7rt|j||fS)NzVocabulary path (z) should be a directory-r) r*r+isdirloggererrorjoinVOCAB_FILES_NAMESabspathrr)r#r:r;out_vocab_files r&save_vocabularyz!FNetTokenizerFast.save_vocabularysww}}^, LL,^,<z[SEP]zz[CLS]z[MASK])N)__name__ __module__ __qualname____doc__rCvocab_files_namesmodel_input_namesr slow_tokenizer_classr"propertyboolr-rintrr6r9r rrF __classcell__)r%s@r&rr&s D*$&67(%%NMMMJN;9;3;DI3F; c;4JNQ9Q3;DI3FQ cQ< !c !HSM !]bcf]g !r'r)rJr*shutilrtypingrrrtokenization_utilsrtokenization_utils_fastr utilsr r tokenization_fnetr get_loggerrGr@rCSPIECE_UNDERLINErr'r&r[sd+ ((,>80M   H %#1EUVT!/T!r'