o ߥi)@sdZddlZddlmZddlmZmZddlmZddl m Z ddl m Z er0dd lmZndZe Z d d d Zd iiZiZiZGddde ZdS)z*Fast Tokenization class for model DeBERTa.N)copyfile)OptionalTuple)is_sentencepiece_available)PreTrainedTokenizerFast)logger)DebertaV2Tokenizerz spm.modelztokenizer.json) vocab_filetokenizer_filer cseZdZdZeZeZeZ e Z e Z            d dfd d Zdd dZ  dfdd Z dddZ ddedeed eefddZZS)DebertaV2TokenizerFasta Constructs a DeBERTa-v2 fast tokenizer. Based on [SentencePiece](https://github.com/google/sentencepiece) and [rjieba-py](https://github.com/messense/rjieba-py). 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. bos_token (`string`, *optional*, defaults to `"[CLS]"`): The beginning of sequence token that was used during pre-training. Can be used a sequence classifier token. When building a sequence using special tokens, this is not the token that is used for the beginning of sequence. The token used is the `cls_token`. eos_token (`string`, *optional*, defaults to `"[SEP]"`): 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 `"[UNK]"`): 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 `"[PAD]"`): 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. NFT[CLS][SEP][UNK][PAD][MASK]returnc  s^tj|f|||||| | | | ||d | ||_||_||_||_|js*d|_dSd|_dS)N) r do_lower_case bos_token eos_token unk_token sep_token pad_token cls_token mask_tokensplit_by_punct split_chineseFT)super__init__rrrr can_save_slow_tokenizer)selfr r rrrrrrrrrrkwargs __class__f/home/ubuntu/.local/lib/python3.10/site-packages/modelscope/models/nlp/deberta_v2/tokenization_fast.pyres, zDebertaV2TokenizerFast.__init__cCs@|dur|jg||jgS|jg}|jg}|||||S)a Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. A DeBERTa 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. N) cls_token_id sep_token_id)r token_ids_0 token_ids_1clssepr$r$r% build_inputs_with_special_tokenss z7DebertaV2TokenizerFast.build_inputs_with_special_tokenscsf|r tj||ddS|dur&dgdgt|dgdgt|dgSdgdgt|dgS)a Retrieves 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` or `encode_plus` methods. 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)already_has_special_tokensNrr)rget_special_tokens_masklen)r r(r)r-r"r$r%r.s z.DebertaV2TokenizerFast.get_special_tokens_maskcCsV|jg}|jg}|durt|||dgSt|||dgt||dgS)a Create a mask from the two sequences passed to be used in a sequence-pair classification task. A DeBERTa sequence pair mask has the following format: ``` 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 | first sequence | second sequence | ``` If `token_ids_1` is `None`, this method only returns the first portion of the mask (0s). Args: token_ids_0 (`List[int]`): List of IDs. token_ids_1 (`List[int]`, *optional*): Optional second list of IDs for sequence pairs. Returns: `List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s). Nrr)r'r&r/)r r(r)r+r*r$r$r%$create_token_type_ids_from_sequencessz;DebertaV2TokenizerFast.create_token_type_ids_from_sequencessave_directoryfilename_prefixcCs~|jstdtj|std|ddStj||r"|dndtd}tj |j tj |kr __classcell__r$r$r"r%r -sH1  $!  r )rBr6shutilrtypingrrtransformers.file_utilsr$transformers.tokenization_utils_fastrmodelscope.utilsrlogging tokenizationr get_loggerr;rDrHrFr r$r$r$r%s$