a h>@sdZddlZddlZddlZddlZddlmZddlmZm Z m Z ddl Z ddl mZddlmZddlmZerdd lmZdd lmZmZdd lmZeeZd d iZdZeddGdddeZdgZdS)z$Tokenization class for SigLIP model.N)copyfile) TYPE_CHECKINGAnyOptional)import_protobuf)PreTrainedTokenizer) AddedToken) TextInput)loggingrequires_backends)requires vocab_filez spiece.modelu▁) sentencepiece)backendscsxeZdZdZeZddgZd8eee e fdd fd d Z d d Z e ddZddZd9eeeeeeeedfdd ZeeeedddZd:eeeeeeedddZd;eeeeeeedddZddZd d!Ze e d"d#d$Zdd%d&d'ZdSiglipTokenizera 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. Z input_idsZattention_maskN@T)sp_model_kwargsreturnc st|dt|tr&t|dddddn|}t|trFt|dddddn|}t|trft|dddddn|}|durvin||_||_||_||_||_t j f|||||j||d| dS)NprotobufTF)rstriplstrip normalizedZspecial) eos_token unk_token pad_tokenadditional_special_tokensrmodel_max_length do_lower_case) r isinstancestrr rr rget_spm_processorsp_modelsuper__init__) selfrrrrrrrr kwargs __class__j/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/siglip/tokenization_siglip.pyr&Zs:  zSiglipTokenizer.__init__cCstjfi|j}t|jdV}|}t}|j|}| }d|_ |j || }||Wdn1sz0Y|S)NrbF)spmSentencePieceProcessorropenrreadrZ ModelProtoZ FromStringZNormalizerSpecZadd_dummy_prefixnormalizer_specZ MergeFromZSerializeToStringZLoadFromSerializedProto)r' tokenizerfr$Z model_pb2modelr2r+r+r,r#s  (z!SiglipTokenizer.get_spm_processorcCs |jSN)r$Zget_piece_sizer'r+r+r, vocab_sizeszSiglipTokenizer.vocab_sizecs(fddtjD}|j|S)Ncsi|]}||qSr+)Zconvert_ids_to_tokens).0ir7r+r, z-SiglipTokenizer.get_vocab..)ranger8updateZadded_tokens_encoder)r'Zvocabr+r7r, get_vocabs zSiglipTokenizer.get_vocabF) token_ids_0 token_ids_1already_has_special_tokensrcsZ|rtj||ddS|dur2dgt|dgSdgt|dgdgt|dgS)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)r+r,rDsz'SiglipTokenizer.get_special_tokens_mask) token_idsrcCsBt|dkr2|d|jkr2td|jd|S||jgSdS)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.N)rE eos_token_idwarningswarnr)r'rFr+r+r,_add_eos_if_not_presents  z'SiglipTokenizer._add_eos_if_not_present)r@rArcCs<|jg}|dur"t||dgSt||||dgS)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)rHrE)r'r@rAZeosr+r+r,$create_token_type_ids_from_sequencessz4SiglipTokenizer.create_token_type_ids_from_sequencescCs,||}|dur|S||}||SdS)a Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. A sequence has the following format: - single sequence: `X ` - pair of sequences: `A B ` Args: token_ids_0 (`list[int]`): List of IDs to which the special tokens will be added. token_ids_1 (`list[int]`, *optional*): Optional second list of IDs for sequence pairs. Returns: `list[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens. N)rK)r'r@rAr+r+r, build_inputs_with_special_tokenss   z0SiglipTokenizer.build_inputs_with_special_tokenscCs|j}d|d<|S)Nr$)__dict__copy)r'stater+r+r, __getstate__s zSiglipTokenizer.__getstate__cCs<||_t|dsi|_tjfi|j|_|j|jdS)Nr)rNhasattrrr.r/r$Loadr)r'dr+r+r, __setstate__s  zSiglipTokenizer.__setstate__)textrcCs|tddtjS)N) translater" maketransstring punctuation)r'rVr+r+r,remove_punctuationsz"SiglipTokenizer.remove_punctuationkeep_punctuation_exact_stringcsH|r$|fdd||D}n |}tdd|}|}|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). c3s|]}|VqdSr6)r\)r9partr7r+r, sz4SiglipTokenizer.canonicalize_text..z\s+ )joinsplitr\resubstrip)r'rVr^r+r7r,canonicalize_texts   z!SiglipTokenizer.canonicalize_textr c sVtjt|tdfi|}t|dkrR|dtkrR|d|jvrR|dd}|S)z8 Converts a string to a list of tokens. rarCrN)r%tokenizeSPIECE_UNDERLINEreplacerEall_special_tokens)r'rVZadd_special_tokensr(tokensr)r+r,rh(s & zSiglipTokenizer.tokenizecCst|jt|jSr6)rEr$encoder"rr7r+r+r,unk_token_length2sz SiglipTokenizer.unk_token_lengthcKsT|j|dd}|jj|td}|jj|j|td}t||jkrP||jdS|S)u* Returns a tokenized string. We de-activated the `add_dummy_prefix` option, thus the sentencepiece internals will always strip any SPIECE_UNDERLINE. For example: `self.sp_model.encode(f"{SPIECE_UNDERLINE}Hey", out_type = str)` will give `['H', 'e', 'y']` instead of `['▁He', 'y']`. Thus we always encode `f"{unk_token}text"` and strip the `unk_token`. Here is an example with `unk_token = ""` and `unk_token_length = 4`. `self.tokenizer.sp_model.encode(" Hey", out_type = str)[4:]`. Nr])Zout_type)rgr$rmr"rrErn)r'rVr(rlr+r+r, _tokenize7s zSiglipTokenizer._tokenizecCs |j|S)z0Converts a token (str) in an id using the vocab.)r$Z piece_to_id)r'tokenr+r+r,_convert_token_to_idLsz$SiglipTokenizer._convert_token_to_idcCs|j|}|S)z=Converts an index (integer) in a token (str) using the vocab.)r$Z IdToPiece)r'indexrpr+r+r,_convert_id_to_tokenQs z$SiglipTokenizer._convert_id_to_tokencCspg}d}d}|D]F}||jvrH|s*|d7}||j||7}d}g}q||d}q||j|7}|S)z:Converts a sequence of tokens (string) in a single string.rWFraT)rkr$decodeappendrf)r'rlZcurrent_sub_tokensZ out_stringZprev_is_specialrpr+r+r,convert_tokens_to_stringVs  z(SiglipTokenizer.convert_tokens_to_string)save_directoryfilename_prefixrcCstj|s"td|ddStj||r6|dndtd}tj|jtj|krztj |jrzt |j|nLtj |jst |d$}|j }||Wdn1s0Y|fS)NzVocabulary path (z) should be a directory-rWrwb)ospathisdirloggererrorrbVOCAB_FILES_NAMESabspathrisfilerr0r$Zserialized_model_protowrite)r'rwrxZout_vocab_filefiZcontent_spiece_modelr+r+r,save_vocabularyjs (  (zSiglipTokenizer.save_vocabulary)rrrNNrT)NF)N)N)F)N)$__name__ __module__ __qualname____doc__rZvocab_files_namesZmodel_input_namesrdictr"rr&r#propertyr8r?listintboolrDrKrLrMrQrUr\rgrhrnrorqrsrvtupler __classcell__r+r+r)r,r-s\(1        r) rr{rdrZrIshutilrtypingrrrrr.Zconvert_slow_tokenizerrZtokenization_utilsrZtokenization_utils_baser r utilsr r Zutils.import_utilsr Z get_loggerrr~rrir__all__r+r+r+r,s,       P