Zj7SrSSKrSSKrSSKrSSKrSSKJr SSKJrJ r SSK r SSK J r SSKJr \(aSSK Jr SS KJrJr SS KJr \R,"\5rS S 0rS r\"SS9"SS\55rS/rg)z$Tokenization class for SigLIP model.N)copyfile) TYPE_CHECKINGAny) AddedToken)SentencePieceBackend) TextInput)loggingrequires_backends)requires vocab_filez spiece.modelu▁) sentencepiece)backendsc ^\rSrSrSr\rSS/rS$S\\ \ 4S-SS4U4Sjjjr \ S 5r S rS%S \\S \\S-S \S\\4U4SjjjrS\\S\\4SjrS&S \\S \\S-S\\4SjjrS&S \\S \\S-S\\4SjjrSrSrS\ S\ 4SjrSS.SjrS'SSS\\ 4U4Sjjjr\ S5rSrSrSrSrS&S \ S!\ S-S\ \ 4S"jjr!S#r"U=r#$)(SiglipTokenizer+ad 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_maskNsp_model_kwargsreturnc `>[US5 [U[5(a [USSSSS9OUn[U[5(a [USSSSS9OUn[U[5(a [USSSSS9OUnUc0OUUlXl[ T U]"SUUUUUURUUS.U D6 g)NprotobufTF)rstriplstrip normalizedspecial)r eos_token unk_token pad_tokenadditional_special_tokensrmodel_max_length do_lower_case)r isinstancestrrrr"super__init__) selfr rrrr rr!r"kwargs __class__s /root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/siglip/tokenization_siglip.pyr'SiglipTokenizer.__init__Xs $ +)S)) yduVZ [ )S)) yduVZ [ )S)) yduVZ [  &5%U(a[TU]XSS9$UcS/[U5-S/-$S/[U5-S/-S/[U5--S/-$)ad Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer `prepare_for_model` method. Args: token_ids_0 (`list[int]`): List of IDs. token_ids_1 (`list[int]`, *optional*): Optional second list of IDs for sequence pairs. already_has_special_tokens (`bool`, *optional*, defaults to `False`): Whether or not the token list is already formatted with special tokens for the model. Returns: `list[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token. T)r>r?r@r)r&get_special_tokens_masklen)r(r>r?r@r*s r+rC'SiglipTokenizer.get_special_tokens_masksw$ &72']a3   C#k**qc1 1c+&&1#-!s;7G1GHA3NNr- token_idsc[U5S:a9USUR:Xa&[R"SURS35 U$XR/-$)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.)rD eos_token_idwarningswarnr)r(rFs r+_add_eos_if_not_present'SiglipTokenizer._add_eos_if_not_presents[ y>A )B-43D3D"D MM,T^^,<=++   1 122 2r-crUR/nUc[X-5S/-$[X-U-U-5S/-$)aw 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. r)rIrD)r(r>r?eoss r+$create_token_type_ids_from_sequences4SiglipTokenizer.create_token_type_ids_from_sequencessL   !  {()QC/ /;${2S89QC??r-cXURU5nUcU$URU5nX-$)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. )rL)r(r>r?s r+ build_inputs_with_special_tokens0SiglipTokenizer.build_inputs_with_special_tokenss9&22;?   66{CK, ,r-cDURR5nSUS'U$)Nr0)__dict__copy)r(states r+ __getstate__SiglipTokenizer.__getstate__s# ""$ j r-cXl[US5(d0Ul[R"S0URD6UlUR R UR5 g)Nrr#)rVhasattrrspmSentencePieceProcessorr0Loadr )r(ds r+ __setstate__SiglipTokenizer.__setstate__sP t.//#%D 22JT5I5IJ  4??+r-textcjUR[RSS[R55$)N) translater% maketransstring punctuation)r(rcs r+remove_punctuation"SiglipTokenizer.remove_punctuations$~~cmmBF4F4FGHHr-keep_punctuation_exact_stringc ^TR(aUR5nU(a+URU4SjURU555nOTR U5n[ R "SSU5nUR5nU$)a]Returns canonicalized `text` (puncuation removed). Args: text (`str`): String to be canonicalized. keep_punctuation_exact_string (`str`, *optional*): If provided, then this exact string is kept. For example providing '{}' will keep any occurrences of '{}' (but will still remove '{' and '}' that appear separately). c3F># UHnTRU5v M g7fr/)rj).0partr(s r+ 4SiglipTokenizer.canonicalize_text..s#6:c$''--:cs!z\s+ )r"lowerjoinsplitrjresubstrip)r(rcrms` r+canonicalize_text!SiglipTokenizer.canonicalize_textsw   ::**Eb:c6D**40Dvvfc4(zz| r-r c >[TU]"[UR[S5-40UD6n[ U5S:a%US[:XaUSUR ;aUSSnU$)z( Converts a string to a list of tokens. rtrBrN)r&tokenizeSPIECE_UNDERLINEreplacerDall_special_tokens)r(rcadd_special_tokensr)tokensr*s r+r~SiglipTokenizer.tokenizese!"2T\\BRTW5X"Xc\bc v;?vay,<<dNeNeAeABZF r-cp[URR[UR555$r/)rDr0encoder%rr2s r+unk_token_length SiglipTokenizer.unk_token_lengths%4==''DNN(;<==r-c URUSS9nURRU[S9nURRURU-[S9n[ U5UR :aX0R S$U$)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:]`. Nrl)out_type)r{r0rr%rrDr)r(rcr)rs r+ _tokenizeSiglipTokenizer._tokenizes%%d$%O%%dS%9%%dnnt&;c%J25f+AVAV2Vv++-.b\bbr-c8URRU5$)z0Converts a token (str) in an id using the vocab.)r0 piece_to_id)r(tokens r+_convert_token_to_id$SiglipTokenizer._convert_token_to_id2s}}((//r-c<URRU5nU$)z=Converts an index (integer) in a token (str) using the vocab.)r0 IdToPiece)r(indexrs r+_convert_id_to_token$SiglipTokenizer._convert_id_to_token6s ''. r-c"/nSnSnUHWnXPR;a2U(dUS- nX0RRU5U-- nSn/nMDURU5 SnMY X0RRU5- nUR 5$)z:Converts a sequence of tokens (string) in a single string.reFrtT)rr0decodeappendrz)r(rcurrent_sub_tokens out_stringprev_is_specialrs r+convert_tokens_to_string(SiglipTokenizer.convert_tokens_to_string;s E///&#%Jmm223EFNN "&%'""))%0"' mm**+=>> !!r-save_directoryfilename_prefixc[RRU5(d[R SUS35 g[RR X(aUS-OS[ S-5n[RRUR5[RRU5:waG[RRUR5(a[URU5 U4$[RRUR5(dC[US5nURR5nURU5 SSS5 U4$U4$!,(df  U4$=f)NzVocabulary path (z) should be a directory-rer wb)ospathisdirloggererrorrvVOCAB_FILES_NAMESabspathr isfileropenr0serialized_model_protowrite)r(rrout_vocab_fileficontent_spiece_models r+save_vocabularySiglipTokenizer.save_vocabularyNs,ww}}^,, LL,^,<zrNN@T)NFr/)F)$__name__ __module__ __qualname____firstlineno____doc__rvocab_files_namesmodel_input_namesdictr%rr'propertyr3r<listintboolrCrLrPrSrYrarjr{r~rrrrrtupler__static_attributes__ __classcell__)r*s@r+rr+s&P*$&67 "&15+ c3h$.+  + + Z.. puO9O379t3COhlO cOO8 3c 3tCy 3GK@9@379t3C@ c@.GK-9-379t3C- c-4 ,IsIsIHL0[QUVYQZ>>c(0 "&!c!C$J!Z_`cZd!!r-r)rrrxrhrJshutilrtypingrrrr]tokenization_utils_baser tokenization_utils_sentencepiecerr utilsr r utils.import_utilsr get_loggerrrrrr__all__r#r-r+rs+ %1D4/*   H %!>2 %&q!*q!'q!h  r-