g8dZddlZddlZddlmZddlmZmZmZm Z m Z ddl Z ddl mZmZddlmZejeZdd iZd ZGd d eZdS) z$Tokenization classes for FNet model.N)copyfile)AnyDictListOptionalTuple) AddedTokenPreTrainedTokenizer)logging vocab_filez spiece.modelu▁c eZdZdZeZddgZ d'd eee e fd d ffd Z e dZ dZdZdZdZde d ee fdZdZdZdZ d(deedededed e f fd Z d)deedeeed eefd Z d*deedeeed!ed eeffd" Z d)deedeeed eefd#Zd)d$e d%ee d ee fd&ZxZS)+ FNetTokenizera Construct an FNet tokenizer. Adapted from [`AlbertTokenizer`]. Based on [SentencePiece](https://github.com/google/sentencepiece). This tokenizer inherits from [`PreTrainedTokenizer`] 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. sp_model_kwargs (`dict`, *optional*): Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for SentencePiece](https://github.com/google/sentencepiece/tree/master/python) can be used, among other things, to set: - `enable_sampling`: Enable subword regularization. - `nbest_size`: Sampling parameters for unigram. Invalid for BPE-Dropout. - `nbest_size = {0,1}`: No sampling is performed. - `nbest_size > 1`: samples from the nbest_size results. - `nbest_size < 0`: assuming that nbest_size is infinite and samples from the all hypothesis (lattice) using forward-filtering-and-backward-sampling algorithm. - `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for BPE-dropout. Attributes: sp_model (`SentencePieceProcessor`): The *SentencePiece* processor that is used for every conversion (string, tokens and IDs). input_idstoken_type_idsFT[SEP][CLS][MASK]Nsp_model_kwargsreturnc Rt| trt| ddn| } t|trt|dn|}t|trt|dn|}t| trt| dn| } | in| |_||_||_||_||_tj di|j|_ |j |tj d|||||||| |jd | dS)NT)lstripspecial)r) do_lower_case remove_space keep_accents unk_token sep_token pad_token cls_token mask_tokenr) isinstancestrr rrrrr spmSentencePieceProcessorsp_modelLoadsuper__init__) selfr rrrrr r!r"r#rkwargs __class__s f/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/fnet/tokenization_fnet.pyr,zFNetTokenizer.__init__Zsb KUU_adJeJeuZ 4FFFFku ;EiQT;U;UdJy$7777[d ;EiQT;U;UdJy$7777[d =G TW=X=XhZ D9999^h %4%z+FNetTokenizer.get_vocab..s)RRRa++A..RRRr1)ranger5updateadded_tokens_encoder)r-vocabs` r0 get_vocabzFNetTokenizer.get_vocabs@RRRR5;Q;QRRR T./// r1cB|j}d|d<|S)Nr))__dict__copy)r-states r0 __getstate__zFNetTokenizer.__getstate__s$ ""$$ j r1c||_t|dsi|_tjdi|j|_|j|jdS)Nrr$)rBhasattrrr'r(r)r*r )r-ds r0 __setstate__zFNetTokenizer.__setstate__s_ t.// &#%D 2JJT5IJJ  4?+++++r1c|jr:d|}n|}|dddd}|js4t jd|}dd|D}|jr| }|S)N z``"z''NFKDc:g|]}tj||Sr$) unicodedata combining)r9cs r0 z1FNetTokenizer.preprocess_text..s(RRRQ9Nq9Q9QRqRRRr1) rjoinstripsplitreplacerrP normalizerlower)r-inputsoutputss r0preprocess_textzFNetTokenizer.preprocess_texts   hhv||~~335566GGG//$,,44T3??  T!+FG<>> !!!r1 token_idsskip_special_tokensclean_up_tokenization_spacesspaces_between_special_tokensc ttjd||||d|}|s|dd}|S)N)rrrrz rr$)r+_decoderW)r-rrrrr.r]r/s r0rzFNetTokenizer._decodes^uww  3)E*G      - 3<<'22D r1 token_ids_0 token_ids_1cR|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-rrsepclss r0 build_inputs_with_special_tokensz.FNetTokenizer.build_inputs_with_special_tokenssJ& ! !  $s* *[ 3&4s::r1already_has_special_tokensc|r$t||dS|3dgdgt|zzdgzdgt|zzdgzSdgdgt|zzdgzS)a Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer `prepare_for_model` method. Args: token_ids_0 (`List[int]`): List of IDs. token_ids_1 (`List[int]`, *optional*): Optional second list of IDs for sequence pairs. already_has_special_tokens (`bool`, *optional*, defaults to `False`): Whether or not the token list is already formatted with special tokens for the model. Returns: `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token. T)rrrNr`r)r+get_special_tokens_maskr4)r-rrrr/s r0rz%FNetTokenizer.get_special_tokens_mask s& & 7722'[]a3   "31#K 0 001QC7A3[AQAQ;QRVWUXX XsqcC ,,,-33r1c|jg}|jg}|t||z|zdgzSt||z|zdgzt||zdgzzS)a Create 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`, this method 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). Nrr`)rrr4rs r0$create_token_type_ids_from_sequencesz2FNetTokenizer.create_token_type_ids_from_sequences&sw, ! !  s[(3.//1#5 53$s*++qc1C c8I4J4JaS4PPPr1save_directoryfilename_prefixctj|s td|ddStj||r|dzndt dz}tj|jtj|kr:tj |jrt|j|nztj |jsVt|d5}|j }||dddn #1swxYwY|fS)NzVocabulary path (z) should be a directory-rNr wb)ospathisdirloggererrorrTVOCAB_FILES_NAMESabspathr isfileropenr)serialized_model_protowrite)r-rrout_vocab_fileficontent_spiece_models r0save_vocabularyzFNetTokenizer.save_vocabularyCsww}}^,,  LLT^TTT U U U F oM_s222QbcoQpp   7??4? + +rw~/N/N N NSUSZSaSabfbqSrSr N T_n 5 5 5 500 /nd++ /r'+}'K'K'M'M$-... / / / / / / / / / / / / / / /  s(/E##E'*E') FTTrrrrrN)FNFr3)NF) __name__ __module__ __qualname____doc__rvocab_files_namesmodel_input_namesrrr&rr,propertyr5r@rErIr\rrnrrrwrintboolrrrrrr __classcell__)r/s@r0rr#s11f*$&67 48) ) "$sCx.1)  ) ) ) ) ) ) V""X"  ,,,   cd3i(...... """,%*-1.3 9"'+  (,  ,JN;;9;3;DI3F; c;;;;4sx44943;DI3F4ko4 c444444:JNQQ9Q3;DI3FQ cQQQQ:!!c!HSM!]bcf]g!!!!!!!!r1r)rrrPshutilrtypingrrrrr sentencepiecer'tokenization_utilsr r utilsr get_loggerrrrrgrr$r1r0rs+* 33333333333333AAAAAAAA  H % %!>2o!o!o!o!o!'o!o!o!o!o!r1