tj7dZddlZddlZddlZddlZddlmZddlmZm Z ddl Z ddl m Z ddlmZerddl mZdd lmZmZdd lmZejeZd d iZd ZedGddeZdgZdS)z$Tokenization class for SigLIP model.N)copyfile) TYPE_CHECKINGAny) AddedToken)SentencePieceBackend) TextInput)loggingrequires_backends)requires vocab_filez spiece.modelu▁) sentencepiece)backendsc eZdZdZeZddgZ d'd eee fdzd dffd Z e d Z d Z d(deedeedzded eeffd Zdeed eefdZ d)deedeedzd eefdZ d)deedeedzd eefdZdZdZded efdZdddZd*ddd eeffd Ze dZd Zd!Zd"Zd#Zd)d$ed%edzd eefd&Z xZ!S)+SiglipTokenizera Construct a Siglip tokenizer. 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. eos_token (`str`, *optional*, defaults to `""`): The end of sequence token. 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. pad_token (`str`, *optional*, defaults to `""`): The token used for padding, for example when batching sequences of different lengths. additional_special_tokens (`list[str]`, *optional*): Additional special tokens used by the tokenizer. 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. model_max_length (`int`, *optional*, defaults to 64): The maximum length (in number of tokens) for model inputs. do_lower_case (`bool`, *optional*, defaults to `True`): Whether or not to lowercase the input when tokenizing. input_idsattention_maskN@Tsp_model_kwargsreturnc t|dt|trt|ddddn|}t|trt|ddddn|}t|trt|ddddn|}|in||_||_t jd||||||j||d| dS)NprotobufTF)rstriplstrip normalizedspecial)r eos_token unk_token pad_tokenadditional_special_tokensrmodel_max_length do_lower_case)r isinstancestrrrr$super__init__) selfr rr r!r"rr#r$kwargs __class__s l/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/siglip/tokenization_siglip.pyr)zSiglipTokenizer.__init__Xs# $ +++)S)) JyduVZ [ [ [ [ )S)) JyduVZ [ [ [ [ )S)) JyduVZ [ [ [ [  &5%z-SiglipTokenizer.get_vocab..s)RRRa++A..RRRr.)ranger4updateadded_tokens_encoder)r*vocabs` r- get_vocabzSiglipTokenizer.get_vocabs@RRRR5;Q;QRRR T./// r.F token_ids_0 token_ids_1already_has_special_tokensc|r$t||dS|dgt|zdgzSdgt|zdgzdgt|zzdgzS)a Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer `prepare_for_model` method. Args: token_ids_0 (`list[int]`): List of IDs. token_ids_1 (`list[int]`, *optional*): Optional second list of IDs for sequence pairs. already_has_special_tokens (`bool`, *optional*, defaults to `False`): Whether or not the token list is already formatted with special tokens for the model. Returns: `list[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token. T)r@rArBNr)r(get_special_tokens_masklen)r*r@rArBr,s r-rEz'SiglipTokenizer.get_special_tokens_masks$ & 7722'[]a3   C#k***qc1 1c+&&&1#-!s;7G7G1GHA3NNr. token_idsct|dkr0|d|jkrtjd|jd|S||jgzS)z.Do not add eos again if user already added it.rzThis sequence already has zQ. In future versions this behavior may lead to duplicated eos tokens being added.)rF eos_token_idwarningswarnr)r*rGs r-_add_eos_if_not_presentz'SiglipTokenizer._add_eos_if_not_presentsi y>>A  )B-43D"D"D M+T^+++     122 2r.cz|jg}|t||zdgzSt||z|z|zdgzS)a Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make use of token type ids, therefore a list of zeros is returned. 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 zeros. Nr)rJrF)r*r@rAeoss r-$create_token_type_ids_from_sequencesz4SiglipTokenizer.create_token_type_ids_from_sequencessS  !  {S())QC/ /;${2S899QC??r.ch||}||S||}||zS)a Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. A sequence has the following format: - single sequence: `X ` - pair of sequences: `A B ` 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. )rM)r*r@rAs r- build_inputs_with_special_tokensz0SiglipTokenizer.build_inputs_with_special_tokenssA&22;??   66{CCK, ,r.cB|j}d|d<|S)Nr1)__dict__copy)r*states r- __getstate__zSiglipTokenizer.__getstate__s$ ""$$ j r.c||_t|dsi|_tjdi|j|_|j|jdS)Nrr%)rThasattrrspmSentencePieceProcessorr1Loadr )r*ds r- __setstate__zSiglipTokenizer.__setstate__s_ t.// &#%D 2JJT5IJJ  4?+++++r.textct|tddtjS)N) translater' maketransstring punctuation)r*r_s r-remove_punctuationz"SiglipTokenizer.remove_punctuations'~~cmmBF4FGGHHHr.keep_punctuation_exact_stringc*jr|}|r5|fd||D}n|}t jdd|}|}|S)aReturns canonicalized `text` (puncuation removed). Args: text (`str`): String to be canonicalized. keep_punctuation_exact_string (`str`, *optional*): If provided, then this exact string is kept. For example providing '{}' will keep any occurrences of '{}' (but will still remove '{' and '}' that appear separately). c3BK|]}|VdSr0)rf)r8partr*s r- z4SiglipTokenizer.canonicalize_text..sB6626''--666666r.z\s+ )r$lowerjoinsplitrfresubstrip)r*r_rhs` r-canonicalize_textz!SiglipTokenizer.canonicalize_texts   ::<**Eb:c:c666DD**400Dvfc4((zz|| r.r c tjt|tdzfi|}t |dkr*|dtkr|d|jvr |dd}|S)z8 Converts a string to a list of tokens. rmrDrN)r(tokenizeSPIECE_UNDERLINEreplacerFall_special_tokens)r*r_add_special_tokensr+tokensr,s r-rvzSiglipTokenizer.tokenizes{"!"2T\\BRTW5X5X"Xcc\bcc v;;??vay,<<<dNeAeAeABBZF r.ctt|jt|jSr0)rFr1encoder'r r3s r-unk_token_lengthz SiglipTokenizer.unk_token_lengths*4=''DN(;(;<<===r.c ||d}|j|t}|j|j|zt}t ||jkr||jdn|S)u* Returns a tokenized string. We de-activated the `add_dummy_prefix` option, thus the sentencepiece internals will always strip any SPIECE_UNDERLINE. For example: `self.sp_model.encode(f"{SPIECE_UNDERLINE}Hey", out_type = str)` will give `['H', 'e', 'y']` instead of `['▁He', 'y']`. Thus we always encode `f"{unk_token}text"` and strip the `unk_token`. Here is an example with `unk_token = ""` and `unk_token_length = 4`. `self.tokenizer.sp_model.encode(" Hey", out_type = str)[4:]`. Nrg)out_type)rtr1r}r'r rFr~)r*r_r+r{s r- _tokenizezSiglipTokenizer._tokenizes%%d$%OO%%dS%99%%dnt&;c%JJ25f++AV2V2Vvd+--..\bbr.c6|j|S)z0Converts a token (str) in an id using the vocab.)r1 piece_to_id)r*tokens r-_convert_token_to_idz$SiglipTokenizer._convert_token_to_id2s}((///r.c:|j|}|S)z=Converts an index (integer) in a token (str) using the vocab.)r1 IdToPiece)r*indexrs r-_convert_id_to_tokenz$SiglipTokenizer._convert_id_to_token6s ''.. r.cg}d}d}|D]N}||jvr,|s|dz }||j||zz }d}g}7||d}O||j|z }|S)z:Converts a sequence of tokens (string) in a single string.raFrmT)ryr1decodeappendrs)r*r{current_sub_tokens out_stringprev_is_specialrs r-convert_tokens_to_stringz(SiglipTokenizer.convert_tokens_to_string;s  ( (E///&&#%Jdm223EFFNN "&%'"""))%000"'dm**+=>>> !!!r.save_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-rar wb)ospathisdirloggererrorroVOCAB_FILES_NAMESabspathr isfileropenr1serialized_model_protowrite)r*rrout_vocab_fileficontent_spiece_models r-save_vocabularyzSiglipTokenizer.save_vocabularyNsww}}^,,  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$-... / / / / / / / / / / / / / / /  s(/E##E'*E')rrrNNrT)NFr0)F)"__name__ __module__ __qualname____doc__rvocab_files_namesmodel_input_namesdictr'rr)propertyr4r?listintboolrErMrPrRrWr^rfrtrvr~rrrrtupler __classcell__)r,s@r-rr+s&&P*$&67 "&15+ + c3h$.+  + + + + + + Z..X. puOO9O379t3COhlO cOOOOOO8 3c 3tCy 3 3 3 3GK@@9@379t3C@ c@@@@.GK--9-379t3C- c----4 ,,,IsIsIIIIHL0[QUVYQZ>>X>ccc(000 """&!!c!C$J!Z_`cZd!!!!!!!!r.r)rrrqrdrKshutilrtypingrrrrZtokenization_utils_baser tokenization_utils_sentencepiecerr utilsr r utils.import_utilsr get_loggerrrrrwr__all__r%r.r-rsU+* %%%%%%%%111111DDDDDD5444444////////******  H % %!>2 %&&&q!q!q!q!q!*q!q!'&q!h  r.