374 lines
15 KiB
Python
374 lines
15 KiB
Python
# These codes are copied from modelscope revision c58451baead80d83281f063d12fb377fad415257
|
|
# Copyright 2022 OFA-Sys Team. All rights reserved.
|
|
#
|
|
# 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 classes for OFA."""
|
|
import collections
|
|
import os
|
|
from typing import List, Optional, Tuple
|
|
|
|
from transformers import PreTrainedTokenizer
|
|
from transformers.models.bart.tokenization_bart import BartTokenizer
|
|
from transformers.models.bert.tokenization_bert import (BasicTokenizer,
|
|
WordpieceTokenizer)
|
|
from transformers.utils import logging
|
|
|
|
from modelscope.utils.constant import ModelFile
|
|
|
|
logger = logging.get_logger()
|
|
|
|
VOCAB_FILES_NAMES = {'vocab_file': 'vocab.json', 'merges_file': 'merges.txt'}
|
|
|
|
PRETRAINED_VOCAB_FILES_MAP = {
|
|
'vocab_file': {
|
|
'ofa-base': 'https://huggingface.co/ofa-base/resolve/main/vocab.json',
|
|
},
|
|
'merges_file': {
|
|
'ofa-base': 'https://huggingface.co/ofa-base/resolve/main/merges.txt',
|
|
},
|
|
# OFA models are implemented to be compatible with both huggingface
|
|
# and modelscope frameworks. For all OFA models available on huggingface,
|
|
# please refer to https://huggingface.co/models?filter=ofa
|
|
}
|
|
|
|
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
|
|
'ofa-base': 1024,
|
|
}
|
|
|
|
VOCAB_FILES_NAMES_ZH = {'vocab_file': ModelFile.VOCAB_FILE}
|
|
|
|
PRETRAINED_VOCAB_FILES_MAP_ZH = {
|
|
'vocab_file': {
|
|
'bert-base-chinese':
|
|
'https://huggingface.co/bert-base-chinese/resolve/main/vocab.txt',
|
|
}
|
|
# OFA models are implemented to be compatible with both huggingface
|
|
# and modelscope frameworks. For all OFA models available on huggingface,
|
|
# please refer to https://huggingface.co/models?filter=ofa
|
|
}
|
|
|
|
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES_ZH = {
|
|
'ofa-base': 1024,
|
|
}
|
|
|
|
PRETRAINED_INIT_CONFIGURATION_ZH = {
|
|
'bert-base-chinese': {
|
|
'do_lower_case': True
|
|
},
|
|
}
|
|
|
|
|
|
class OFATokenizer(BartTokenizer):
|
|
"""
|
|
Construct a OFA tokenizer.
|
|
|
|
[`~OFATokenizer`] is identical to [`BartTokenizer`] and runs end-to-end tokenization: punctuation splitting and
|
|
wordpiece.
|
|
|
|
Refer to superclass [`BartTokenizer`] for usage examples and documentation concerning parameters.
|
|
"""
|
|
|
|
vocab_files_names = VOCAB_FILES_NAMES
|
|
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
|
|
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
|
|
|
|
|
|
def load_vocab(vocab_file):
|
|
"""Loads a vocabulary file into a dictionary."""
|
|
vocab = collections.OrderedDict()
|
|
with open(vocab_file, 'r', encoding='utf-8') as reader:
|
|
tokens = reader.readlines()
|
|
for index, token in enumerate(tokens):
|
|
token = token.rstrip('\n')
|
|
vocab[token] = index
|
|
return vocab
|
|
|
|
|
|
def whitespace_tokenize(text):
|
|
"""Runs basic whitespace cleaning and splitting on a piece of text."""
|
|
text = text.strip()
|
|
if not text:
|
|
return []
|
|
tokens = text.split()
|
|
return tokens
|
|
|
|
|
|
class OFATokenizerZH(PreTrainedTokenizer):
|
|
r"""
|
|
Construct a OFA tokenizer. Based on WordPiece.
|
|
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`):
|
|
File containing the vocabulary.
|
|
do_lower_case (`bool`, *optional*, defaults to `True`):
|
|
Whether or not to lowercase the input when tokenizing.
|
|
do_basic_tokenize (`bool`, *optional*, defaults to `True`):
|
|
Whether or not to do basic tokenization before WordPiece.
|
|
never_split (`Iterable`, *optional*):
|
|
Collection of tokens which will never be split during tokenization. Only has an effect when
|
|
`do_basic_tokenize=True`
|
|
bos_token (`str`, *optional*, defaults to `"<s>"`):
|
|
The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
|
|
|
|
<Tip>
|
|
|
|
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`.
|
|
|
|
</Tip>
|
|
|
|
eos_token (`str`, *optional*, defaults to `"</s>"`):
|
|
The end of sequence token.
|
|
|
|
<Tip>
|
|
|
|
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`.
|
|
|
|
</Tip>
|
|
|
|
sep_token (`str`, *optional*, defaults to `"</s>"`):
|
|
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 `"<s>"`):
|
|
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.
|
|
tokenize_chinese_chars (`bool`, *optional*, defaults to `True`):
|
|
Whether or not to tokenize Chinese characters.
|
|
|
|
This should likely be deactivated for Japanese (see this
|
|
[issue](https://github.com/huggingface/transformers/issues/328)).
|
|
strip_accents (`bool`, *optional*):
|
|
Whether or not to strip all accents. If this option is not specified, then it will be determined by the
|
|
value for `lowercase` (as in the original BERT).
|
|
"""
|
|
|
|
vocab_files_names = VOCAB_FILES_NAMES_ZH
|
|
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP_ZH
|
|
pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION_ZH
|
|
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES_ZH
|
|
|
|
def __init__(self,
|
|
vocab_file,
|
|
do_lower_case=True,
|
|
do_basic_tokenize=True,
|
|
never_split=None,
|
|
bos_token='<s>',
|
|
eos_token='</s>',
|
|
sep_token='</s>',
|
|
cls_token='<s>',
|
|
unk_token='<unk>',
|
|
pad_token='<pad>',
|
|
mask_token='<mask>',
|
|
tokenize_chinese_chars=True,
|
|
strip_accents=None,
|
|
**kwargs):
|
|
super().__init__(
|
|
do_lower_case=do_lower_case,
|
|
do_basic_tokenize=do_basic_tokenize,
|
|
never_split=never_split,
|
|
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,
|
|
tokenize_chinese_chars=tokenize_chinese_chars,
|
|
strip_accents=strip_accents,
|
|
**kwargs,
|
|
)
|
|
|
|
if not os.path.isfile(vocab_file):
|
|
raise ValueError(
|
|
f"Can't find a vocabulary file at path '{vocab_file}'. To load the vocabulary from a Google pretrained "
|
|
'model use `tokenizer = BertTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`'
|
|
)
|
|
self.vocab = load_vocab(vocab_file)
|
|
self.ids_to_tokens = collections.OrderedDict([
|
|
(ids, tok) for tok, ids in self.vocab.items()
|
|
])
|
|
self.do_basic_tokenize = do_basic_tokenize
|
|
if do_basic_tokenize:
|
|
self.basic_tokenizer = BasicTokenizer(
|
|
do_lower_case=do_lower_case,
|
|
never_split=never_split,
|
|
tokenize_chinese_chars=tokenize_chinese_chars,
|
|
strip_accents=strip_accents,
|
|
)
|
|
self.wordpiece_tokenizer = WordpieceTokenizer(
|
|
vocab=self.vocab, unk_token=self.unk_token)
|
|
|
|
@property
|
|
def do_lower_case(self):
|
|
return self.basic_tokenizer.do_lower_case
|
|
|
|
@property
|
|
def vocab_size(self):
|
|
return len(self.vocab)
|
|
|
|
def get_vocab(self):
|
|
return dict(self.vocab, **self.added_tokens_encoder)
|
|
|
|
def _tokenize(self, text):
|
|
split_tokens = []
|
|
if self.do_basic_tokenize:
|
|
for token in self.basic_tokenizer.tokenize(
|
|
text, never_split=self.all_special_tokens):
|
|
|
|
# If the token is part of the never_split set
|
|
if token in self.basic_tokenizer.never_split:
|
|
split_tokens.append(token)
|
|
else:
|
|
split_tokens += self.wordpiece_tokenizer.tokenize(token)
|
|
else:
|
|
split_tokens = self.wordpiece_tokenizer.tokenize(text)
|
|
return split_tokens
|
|
|
|
def _convert_token_to_id(self, token):
|
|
"""Converts a token (str) in an id using the vocab."""
|
|
return self.vocab.get(token, self.vocab.get(self.unk_token))
|
|
|
|
def _convert_id_to_token(self, index):
|
|
"""Converts an index (integer) in a token (str) using the vocab."""
|
|
return self.ids_to_tokens.get(index, self.unk_token)
|
|
|
|
def convert_tokens_to_string(self, tokens):
|
|
"""Converts a sequence of tokens (string) in a single string."""
|
|
out_string = ' '.join(tokens).replace(' ##', '').strip()
|
|
return out_string
|
|
|
|
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 BERT 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]:
|
|
"""
|
|
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.
|
|
"""
|
|
|
|
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 not None:
|
|
return [1] + ([0] * len(token_ids_0)) + [1] + (
|
|
[0] * len(token_ids_1)) + [1]
|
|
return [1] + ([0] * len(token_ids_0)) + [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 BERT 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]
|
|
|
|
def save_vocabulary(self,
|
|
save_directory: str,
|
|
filename_prefix: Optional[str] = None) -> Tuple[str]:
|
|
index = 0
|
|
if os.path.isdir(save_directory):
|
|
vocab_file = os.path.join(
|
|
save_directory,
|
|
(filename_prefix + '-' if filename_prefix else '')
|
|
+ VOCAB_FILES_NAMES['vocab_file'])
|
|
else:
|
|
vocab_file = (filename_prefix
|
|
+ '-' if filename_prefix else '') + save_directory
|
|
with open(vocab_file, 'w', encoding='utf-8') as writer:
|
|
for token, token_index in sorted(
|
|
self.vocab.items(), key=lambda kv: kv[1]):
|
|
if index != token_index:
|
|
logger.warning(
|
|
f'Saving vocabulary to {vocab_file}: vocabulary indices are not consecutive.'
|
|
' Please check that the vocabulary is not corrupted!')
|
|
index = token_index
|
|
writer.write(token + '\n')
|
|
index += 1
|
|
return (vocab_file, )
|