# coding=utf-8 # Copyright 2020 Microsoft and the HuggingFace Inc. team. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. """ Tokenization class for model DeBERTa.""" import json import os from typing import List, Optional, Tuple import regex as re from ...tokenization_utils import AddedToken, PreTrainedTokenizer from ...utils import logging logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt"} PRETRAINED_VOCAB_FILES_MAP = { "vocab_file": { "microsoft/deberta-base": "https://huggingface.co/microsoft/deberta-base/resolve/main/vocab.json", "microsoft/deberta-large": "https://huggingface.co/microsoft/deberta-large/resolve/main/vocab.json", "microsoft/deberta-xlarge": "https://huggingface.co/microsoft/deberta-xlarge/resolve/main/vocab.json", "microsoft/deberta-base-mnli": "https://huggingface.co/microsoft/deberta-base-mnli/resolve/main/vocab.json", "microsoft/deberta-large-mnli": "https://huggingface.co/microsoft/deberta-large-mnli/resolve/main/vocab.json", "microsoft/deberta-xlarge-mnli": ( "https://huggingface.co/microsoft/deberta-xlarge-mnli/resolve/main/vocab.json" ), }, "merges_file": { "microsoft/deberta-base": "https://huggingface.co/microsoft/deberta-base/resolve/main/merges.txt", "microsoft/deberta-large": "https://huggingface.co/microsoft/deberta-large/resolve/main/merges.txt", "microsoft/deberta-xlarge": "https://huggingface.co/microsoft/deberta-xlarge/resolve/main/merges.txt", "microsoft/deberta-base-mnli": "https://huggingface.co/microsoft/deberta-base-mnli/resolve/main/merges.txt", "microsoft/deberta-large-mnli": "https://huggingface.co/microsoft/deberta-large-mnli/resolve/main/merges.txt", "microsoft/deberta-xlarge-mnli": ( "https://huggingface.co/microsoft/deberta-xlarge-mnli/resolve/main/merges.txt" ), }, } PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { "microsoft/deberta-base": 512, "microsoft/deberta-large": 512, "microsoft/deberta-xlarge": 512, "microsoft/deberta-base-mnli": 512, "microsoft/deberta-large-mnli": 512, "microsoft/deberta-xlarge-mnli": 512, } PRETRAINED_INIT_CONFIGURATION = { "microsoft/deberta-base": {"do_lower_case": False}, "microsoft/deberta-large": {"do_lower_case": False}, } # Copied from transformers.models.gpt2.tokenization_gpt2.bytes_to_unicode def bytes_to_unicode(): """ Returns list of utf-8 byte and a mapping to unicode strings. We specifically avoids mapping to whitespace/control characters the bpe code barfs on. The reversible bpe codes work on unicode strings. This means you need a large # of unicode characters in your vocab if you want to avoid UNKs. When you're at something like a 10B token dataset you end up needing around 5K for decent coverage. This is a significant percentage of your normal, say, 32K bpe vocab. To avoid that, we want lookup tables between utf-8 bytes and unicode strings. """ bs = ( list(range(ord("!"), ord("~") + 1)) + list(range(ord("¡"), ord("¬") + 1)) + list(range(ord("®"), ord("ÿ") + 1)) ) cs = bs[:] n = 0 for b in range(2**8): if b not in bs: bs.append(b) cs.append(2**8 + n) n += 1 cs = [chr(n) for n in cs] return dict(zip(bs, cs)) # Copied from transformers.models.gpt2.tokenization_gpt2.get_pairs def get_pairs(word): """ Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings). """ pairs = set() prev_char = word[0] for char in word[1:]: pairs.add((prev_char, char)) prev_char = char return pairs class DebertaTokenizer(PreTrainedTokenizer): """ Construct a DeBERTa tokenizer. Based on byte-level Byte-Pair-Encoding. This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will be encoded differently whether it is at the beginning of the sentence (without space) or not: ```python >>> from transformers import DebertaTokenizer >>> tokenizer = DebertaTokenizer.from_pretrained("microsoft/deberta-base") >>> tokenizer("Hello world")["input_ids"] [1, 31414, 232, 2] >>> tokenizer(" Hello world")["input_ids"] [1, 20920, 232, 2] ``` You can get around that behavior by passing `add_prefix_space=True` when instantiating this tokenizer or when you call it on some text, but since the model was not pretrained this way, it might yield a decrease in performance. When used with `is_split_into_words=True`, this tokenizer will add a space before each word (even the first one). 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`): Path to the vocabulary file. merges_file (`str`): Path to the merges file. errors (`str`, *optional*, defaults to `"replace"`): Paradigm to follow when decoding bytes to UTF-8. See [bytes.decode](https://docs.python.org/3/library/stdtypes.html#bytes.decode) for more information. bos_token (`str`, *optional*, defaults to `"[CLS]"`): The beginning of sequence token. eos_token (`str`, *optional*, defaults to `"[SEP]"`): The end of sequence token. 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. 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. 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. pad_token (`str`, *optional*, defaults to `"[PAD]"`): The token used for padding, for example when batching sequences of different lengths. 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. 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. (Deberta tokenizer detect beginning of words by the preceding space). add_bos_token (`bool`, *optional*, defaults to `False`): Whether or not to add an initial <|endoftext|> to the input. This allows to treat the leading word just as any other word. """ vocab_files_names = VOCAB_FILES_NAMES pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask", "token_type_ids"] def __init__( self, vocab_file, merges_file, errors="replace", bos_token="[CLS]", eos_token="[SEP]", sep_token="[SEP]", cls_token="[CLS]", unk_token="[UNK]", pad_token="[PAD]", mask_token="[MASK]", add_prefix_space=False, add_bos_token=False, **kwargs, ): bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token sep_token = AddedToken(sep_token, lstrip=False, rstrip=False) if isinstance(sep_token, str) else sep_token cls_token = AddedToken(cls_token, lstrip=False, rstrip=False) if isinstance(cls_token, str) else cls_token unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token # Mask token behave like a normal word, i.e. include the space before it mask_token = AddedToken(mask_token, lstrip=True, rstrip=False) if isinstance(mask_token, str) else mask_token self.add_bos_token = add_bos_token with open(vocab_file, encoding="utf-8") as vocab_handle: self.encoder = json.load(vocab_handle) self.decoder = {v: k for k, v in self.encoder.items()} self.errors = errors # how to handle errors in decoding self.byte_encoder = bytes_to_unicode() self.byte_decoder = {v: k for k, v in self.byte_encoder.items()} with open(merges_file, encoding="utf-8") as merges_handle: bpe_merges = merges_handle.read().split("\n")[1:-1] bpe_merges = [tuple(merge.split()) for merge in bpe_merges] self.bpe_ranks = dict(zip(bpe_merges, range(len(bpe_merges)))) self.cache = {} self.add_prefix_space = add_prefix_space # Should have added re.IGNORECASE so BPE merges can happen for capitalized versions of contractions self.pat = re.compile(r"""'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+""") super().__init__( errors=errors, bos_token=bos_token, eos_token=eos_token, unk_token=unk_token, sep_token=sep_token, cls_token=cls_token, pad_token=pad_token, mask_token=mask_token, add_prefix_space=add_prefix_space, add_bos_token=add_bos_token, **kwargs, ) @property # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer.vocab_size def vocab_size(self): return len(self.encoder) # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer.get_vocab def get_vocab(self): return dict(self.encoder, **self.added_tokens_encoder) # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer.bpe def bpe(self, token): if token in self.cache: return self.cache[token] word = tuple(token) pairs = get_pairs(word) if not pairs: return token while True: bigram = min(pairs, key=lambda pair: self.bpe_ranks.get(pair, float("inf"))) if bigram not in self.bpe_ranks: break first, second = bigram new_word = [] i = 0 while i < len(word): try: j = word.index(first, i) except ValueError: new_word.extend(word[i:]) break else: new_word.extend(word[i:j]) i = j if word[i] == first and i < len(word) - 1 and word[i + 1] == second: new_word.append(first + second) i += 2 else: new_word.append(word[i]) i += 1 new_word = tuple(new_word) word = new_word if len(word) == 1: break else: pairs = get_pairs(word) word = " ".join(word) self.cache[token] = word return word def build_inputs_with_special_tokens( self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None ) -> List[int]: """ 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. """ if token_ids_1 is None: return [self.cls_token_id] + token_ids_0 + [self.sep_token_id] cls = [self.cls_token_id] sep = [self.sep_token_id] return cls + token_ids_0 + sep + token_ids_1 + sep def get_special_tokens_mask( self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False ) -> List[int]: """ 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. """ if already_has_special_tokens: return super().get_special_tokens_mask( token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True ) if token_ids_1 is None: return [1] + ([0] * len(token_ids_0)) + [1] return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1] def create_token_type_ids_from_sequences( self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None ) -> List[int]: """ 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). """ sep = [self.sep_token_id] cls = [self.cls_token_id] if token_ids_1 is None: return len(cls + token_ids_0 + sep) * [0] return len(cls + token_ids_0 + sep) * [0] + len(token_ids_1 + sep) * [1] # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer._tokenize def _tokenize(self, text): """Tokenize a string.""" bpe_tokens = [] for token in re.findall(self.pat, text): token = "".join( self.byte_encoder[b] for b in token.encode("utf-8") ) # Maps all our bytes to unicode strings, avoiding control tokens of the BPE (spaces in our case) bpe_tokens.extend(bpe_token for bpe_token in self.bpe(token).split(" ")) return bpe_tokens # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer._convert_token_to_id def _convert_token_to_id(self, token): """Converts a token (str) in an id using the vocab.""" return self.encoder.get(token, self.encoder.get(self.unk_token)) # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer._convert_id_to_token def _convert_id_to_token(self, index): """Converts an index (integer) in a token (str) using the vocab.""" return self.decoder.get(index) # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer.convert_tokens_to_string def convert_tokens_to_string(self, tokens): """Converts a sequence of tokens (string) in a single string.""" text = "".join(tokens) text = bytearray([self.byte_decoder[c] for c in text]).decode("utf-8", errors=self.errors) return text # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer.save_vocabulary def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]: if not os.path.isdir(save_directory): logger.error(f"Vocabulary path ({save_directory}) should be a directory") return vocab_file = os.path.join( save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"] ) merge_file = os.path.join( save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["merges_file"] ) with open(vocab_file, "w", encoding="utf-8") as f: f.write(json.dumps(self.encoder, indent=2, sort_keys=True, ensure_ascii=False) + "\n") index = 0 with open(merge_file, "w", encoding="utf-8") as writer: writer.write("#version: 0.2\n") for bpe_tokens, token_index in sorted(self.bpe_ranks.items(), key=lambda kv: kv[1]): if index != token_index: logger.warning( f"Saving vocabulary to {merge_file}: BPE merge indices are not consecutive." " Please check that the tokenizer is not corrupted!" ) index = token_index writer.write(" ".join(bpe_tokens) + "\n") index += 1 return vocab_file, merge_file def prepare_for_tokenization(self, text, is_split_into_words=False, **kwargs): add_prefix_space = kwargs.pop("add_prefix_space", self.add_prefix_space) if (is_split_into_words or add_prefix_space) and (len(text) > 0 and not text[0].isspace()): text = " " + text return (text, kwargs)