o ۷iM@sdZddlZddlZddlZddlmZddlmZmZm Z ddl Z ddl m Z ddlmZddlmZerddZ e ddZeddZddZ d?deedeeeded eeffdd ZddZddZd eed eefd!d"Z d@deedeeed eefd#d$Z d@deedeeed eefd%d&Zd'd(Zd)d*Zd+d,d ee ffd-d. Zed/d0Zd1d2Zd3d4Z d5d6Z!d7d8Z"d@d9e d:ee d e#e fd;d<Z$Z%S)A T5Tokenizera Construct a T5 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. When building a sequence using special tokens, this is not the token that is used for the end of sequence. The token used is the `sep_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. extra_ids (`int`, *optional*, defaults to 100): Add a number of extra ids added to the vocabulary for use as sentinels. These tokens are accessible as "" where "{%d}" is a number between 0 and extra_ids-1. These tokens can be retrieved by calling get_sentinel_tokens method and token ids can be by calling get_sentinel_token_ids method 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. legacy (`bool`, *optional*): Whether or not the `legacy` behaviour of the tokenizer should be used. Legacy is before the merge of #24622 and #25224 which includes fixes to properly handle tokens that appear after special tokens. A simple example: - `legacy=True`: ```python >>> from transformers import T5Tokenizer >>> tokenizer = T5Tokenizer.from_pretrained("google-t5/t5-base", legacy=True) >>> tokenizer.encode("Hello .") [8774, 32099, 3, 5, 1] ``` - `legacy=False`: ```python >>> from transformers import T5Tokenizer >>> tokenizer = T5Tokenizer.from_pretrained("google-t5/t5-base", legacy=False) >>> tokenizer.encode("Hello .") # the extra space `[3]` is no longer here [8774, 32099, 5, 1] ``` Checkout the [pull request](https://github.com/huggingface/transformers/pull/24565) for more details. add_prefix_space (`bool`, *optional*, defaults to `False`): Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word. Attributes: sp_model (`SentencePieceProcessor`): The *SentencePiece* processor that is used for every conversion (string, tokens and IDs). input_idsattention_maskdNTsp_model_kwargsreturnc st|tr t|ddn|}t|trt|ddn|}t|tr%t|ddn|}|dur-in||_||_||_tjdi|j|_|j ||durydd|D} t | dkrc|ddt |D7}n!|dkrx|t | krxt d|d |d n d dt |D} | }i|_ t t | D]} td | d dddddd|j t |jd|| <q|durtd|jdd}||_|| dd|_| |_tjd||||||j|| d| dS)NT)specialcSsg|] }dt|vr|qS) sz(T5Tokenizer.__init__..cSg|]}d|dqSr>rrirrrr rzBoth extra_ids (z!) and additional_special_tokens (zk) are provided to T5Tokenizer. In this case the additional_special_tokens must include the extra_ids tokenscSr"r#rr%rrrr r'rr$F) single_wordlstriprstripr normalizedz2You are using the default legacy behaviour of the a_. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565 from_slow) eos_token unk_token pad_token extra_idsadditional_special_tokensrlegacyadd_prefix_spacer) isinstancerr rr _extra_idsspmSentencePieceProcessorsp_modelLoadlenrange ValueError_added_tokens_decoderlogger warning_once __class__r2get_spm_processorpopr3super__init__) selfr r-r.r/r0r1rr2r3kwargs extra_tokensr&r@rrrDsX      zT5Tokenizer.__init__FcCstjdi|j}|js|r||j|St|jd3}|}td|j j d}|j |}| }d|_|j||}||Wd|S1sRwY|S)NrbzThe new behaviour of z (with `self.legacy = False`)Fr)r6r7rr2r9r openreadrr@__name__ ModelProto FromStringNormalizerSpecadd_dummy_prefixnormalizer_spec MergeFromSerializeToStringLoadFromSerializedProto)rEr, tokenizerfr8 model_pb2modelrQrrrrAs"        zT5Tokenizer.get_spm_processorc CsZ|tjvr+tj|}|dur||kr|S|dur+td|d|d|d|d t|S)NzGThis tokenizer was incorrectly instantiated with a model max length of z which will be corrected in Transformers v5. For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. - Be aware that you SHOULD NOT rely on z( automatically truncating your input to zM when padding/encoding. - If you want to encode/pad to sequences longer than z you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. - To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value.)rmax_model_input_sizeswarningswarn FutureWarning)pretrained_model_name_or_pathmax_model_lengthinit_max_model_lengthdeprecated_max_model_lengthrrr!_eventually_correct_t5_max_lengths$    z-T5Tokenizer._eventually_correct_t5_max_lengthcCs |jSN)r8get_piece_sizerErrr vocab_sizes zT5Tokenizer.vocab_sizecs(fddtjD}|j|S)Ncsi|]}||qSr)convert_ids_to_tokensr%rdrr r'z)T5Tokenizer.get_vocab..)r;reupdateadded_tokens_encoder)rEvocabrrdr get_vocabs zT5Tokenizer.get_vocab token_ids_0 token_ids_1already_has_special_tokenscsZ|r tj||ddS|durdgt|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)rlrmrnNrr!)rCget_special_tokens_maskr:)rErlrmrnrHrrros(z#T5Tokenizer.get_special_tokens_maskcCstttdd|jS)NcSsttd|duS)Nz)boolresearch)rrrrsz1T5Tokenizer.get_sentinel_tokens..)listsetfilterr1rdrrrget_sentinel_tokensszT5Tokenizer.get_sentinel_tokenscsfddDS)Ncsg|]}|qSr)convert_tokens_to_ids)rtokenrdrrr sz6T5Tokenizer.get_sentinel_token_ids..)rwrdrrdrget_sentinel_token_idssz"T5Tokenizer.get_sentinel_token_ids token_idscCs>t|dkr|d|jkrtd|jd|S||jgS)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.)r: eos_token_idrZr[r-)rEr{rrr_add_eos_if_not_presents   z#T5Tokenizer._add_eos_if_not_presentcCs<|jg}|durt||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)r}r:)rErlrmeosrrr$create_token_type_ids_from_sequences'sz0T5Tokenizer.create_token_type_ids_from_sequencescCs(||}|dur |S||}||S)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)r~)rErlrmrrr build_inputs_with_special_tokens=s  z,T5Tokenizer.build_inputs_with_special_tokenscCs|j}d|d<|S)Nr8)__dict__copy)rEstaterrr __getstate__Ws zT5Tokenizer.__getstate__cCs<||_t|ds i|_tjdi|j|_|j|jdS)Nrr)rhasattrrr6r7r8r9r )rEdrrr __setstate__\s  zT5Tokenizer.__setstate__textr c s|js t|dkrtj|fi|S|td}|jr t|}tj|fi|}t|dkrC|dtkrC|d|jvrC|dd}|S)z Converts a string to a list of tokens. If `self.legacy` is set to `False`, a prefix token is added unless the first token is special. r r!N)r2r:rCtokenizereplaceSPIECE_UNDERLINEr3all_special_tokensrErrFtokensrHrrrfs & zT5Tokenizer.tokenizecCst|jt|jSrb)r:r8encoderr.rdrrrunk_token_lengthxszT5Tokenizer.unk_token_lengthcKsZ|js |tdfs|jj|tdS|jj|j|td}t||jkr+||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:]`. r)out_typeN) r2 startswithrr8rrr.r:rrrrr _tokenize|s  zT5Tokenizer._tokenizecCs |j|S)z0Converts a token (str) in an id using the vocab.)r8 piece_to_id)rEryrrr_convert_token_to_ids z T5Tokenizer._convert_token_to_idcCs|j|}|S)z=Converts an index (integer) in a token (str) using the vocab.)r8 IdToPiece)rEindexryrrr_convert_id_to_tokens z T5Tokenizer._convert_id_to_tokencCs|dtr|jr|ddd|d<g}d}d}|D]#}||jvr8|s)|d7}||j||7}d}g}q||d}q||j|7}|S)z:Converts a sequence of tokens (string) in a single string.rr!NFrT)rrr3rr8decodeappendstrip)rErcurrent_sub_tokens out_stringprev_is_specialryrrrconvert_tokens_to_strings   z$T5Tokenizer.convert_tokens_to_stringsave_directoryfilename_prefixcCstj|std|ddStj||r|dndtd}tj|jtj|kr?tj |jr?t |j||fStj |jsgt |d}|j }||Wd|fS1sbwY|fS)NzVocabulary path (z) should be a directory-rr wb)ospathisdirr>errorjoinVOCAB_FILES_NAMESabspathr isfilerrJr8serialized_model_protowrite)rErrout_vocab_fileficontent_spiece_modelrrrsave_vocabularys" (     zT5Tokenizer.save_vocabulary)rrrrNNNT)F)NFrb)&rL __module__ __qualname____doc__rvocab_files_namesmodel_input_namesrdictrrrDrA staticmethodrapropertyrerkrtintrprorwrzr~rrrrrrrrrrtupler __classcell__rrrHrr,s|N  I          (r)rrrqrZshutilrtypingrrrrr6convert_slow_tokenizerrtokenization_utilsrtokenization_utils_baser r utilsr utils.import_utilsr get_loggerrLr>rrr__all__rrrrs.