SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Add MP Net 2 (#9004)

Browse Source
This commit is contained in:
StillKeepTry
2020-12-09 10:25:31 -05:00
committed by Lysandre
parent 8729109855
commit df2af6d8b8
21 changed files with 4248 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
src/transformers/models/mpnet/__init__.py Normal file
View File

@@ -0,0 +1,38 @@
# flake8: noqa
# There's no way to ignore "F401 '...' imported but unused" warnings in this
# module, but to preserve other warnings. So, don't check this module at all.
from ...file_utils import is_flax_available, is_tf_available, is_tokenizers_available, is_torch_available
from .configuration_mpnet import MPNET_PRETRAINED_CONFIG_ARCHIVE_MAP, MPNetConfig
from .tokenization_mpnet import MPNetTokenizer
if is_tokenizers_available():
from .tokenization_mpnet_fast import MPNetTokenizerFast
if is_torch_available():
from .modeling_mpnet import (
MPNET_PRETRAINED_MODEL_ARCHIVE_LIST,
MPNetForMaskedLM,
MPNetForMultipleChoice,
MPNetForQuestionAnswering,
MPNetForSequenceClassification,
MPNetForTokenClassification,
MPNetLayer,
MPNetModel,
MPNetPreTrainedModel,
)
if is_tf_available():
from .modeling_tf_mpnet import (
TF_MPNET_PRETRAINED_MODEL_ARCHIVE_LIST,
TFMPNetEmbeddings,
TFMPNetForMaskedLM,
TFMPNetForMultipleChoice,
TFMPNetForQuestionAnswering,
TFMPNetForSequenceClassification,
TFMPNetForTokenClassification,
TFMPNetMainLayer,
TFMPNetModel,
TFMPNetPreTrainedModel,
)

116
src/transformers/models/mpnet/configuration_mpnet.py Normal file
View File

@@ -0,0 +1,116 @@
# coding=utf-8
# Copyright 2018 The HuggingFace Inc. team, Microsoft Corporation.
# Copyright (c) 2018, NVIDIA CORPORATION. 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.
""" MPNet model configuration """
from ...configuration_utils import PretrainedConfig
from ...utils import logging
logger = logging.get_logger(__name__)
MPNET_PRETRAINED_CONFIG_ARCHIVE_MAP = {
"microsoft/mpnet-base": "https://huggingface.co/microsoft/mpnet-base/resolve/main/config.json",
}
class MPNetConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a :class:`~transformers.MPNetModel` or a
:class:`~transformers.TFMPNetModel`. It is used to instantiate a MPNet model according to the specified arguments,
defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration
to that of the MPNet `mpnet-base <https://huggingface.co/mpnet-base>`__ architecture.
Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model
outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information.
Args:
vocab_size (:obj:`int`, `optional`, defaults to 30527):
Vocabulary size of the MPNet model. Defines the number of different tokens that can be represented by the
:obj:`inputs_ids` passed when calling :class:`~transformers.MPNetModel` or
:class:`~transformers.TFMPNetModel`.
hidden_size (:obj:`int`, `optional`, defaults to 768):
Dimensionality of the encoder layers and the pooler layer.
num_hidden_layers (:obj:`int`, `optional`, defaults to 12):
Number of hidden layers in the Transformer encoder.
num_attention_heads (:obj:`int`, `optional`, defaults to 12):
Number of attention heads for each attention layer in the Transformer encoder.
intermediate_size (:obj:`int`, `optional`, defaults to 3072):
Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
hidden_act (:obj:`str` or :obj:`Callable`, `optional`, defaults to :obj:`"gelu"`):
The non-linear activation function (function or string) in the encoder and pooler. If string,
:obj:`"gelu"`, :obj:`"relu"`, :obj:`"silu"` and :obj:`"gelu_new"` are supported.
hidden_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
attention_probs_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
The dropout ratio for the attention probabilities.
max_position_embeddings (:obj:`int`, `optional`, defaults to 512):
The maximum sequence length that this model might ever be used with. Typically set this to something large
just in case (e.g., 512 or 1024 or 2048).
initializer_range (:obj:`float`, `optional`, defaults to 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
layer_norm_eps (:obj:`float`, `optional`, defaults to 1e-12):
The epsilon used by the layer normalization layers.
relative_attention_num_buckets (:obj:`int`, `optional`, defaults to 32):
The number of buckets to use for each attention layer.
Examples::
>>> from transformers import MPNetModel, MPNetConfig
>>> # Initializing a MPNet mpnet-base style configuration
>>> configuration = MPNetConfig()
>>> # Initializing a model from the mpnet-base style configuration
>>> model = MPNetModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
"""
model_type = "mpnet"
def __init__(
self,
vocab_size=30527,
hidden_size=768,
num_hidden_layers=12,
num_attention_heads=12,
intermediate_size=3072,
hidden_act="gelu",
hidden_dropout_prob=0.1,
attention_probs_dropout_prob=0.1,
max_position_embeddings=512,
initializer_range=0.02,
layer_norm_eps=1e-12,
relative_attention_num_buckets=32,
pad_token_id=1,
bos_token_id=0,
eos_token_id=2,
**kwargs,
):
super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
self.vocab_size = vocab_size
self.hidden_size = hidden_size
self.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
self.hidden_act = hidden_act
self.intermediate_size = intermediate_size
self.hidden_dropout_prob = hidden_dropout_prob
self.attention_probs_dropout_prob = attention_probs_dropout_prob
self.max_position_embeddings = max_position_embeddings
self.initializer_range = initializer_range
self.layer_norm_eps = layer_norm_eps
self.relative_attention_num_buckets = relative_attention_num_buckets

1070
src/transformers/models/mpnet/modeling_mpnet.py Normal file
View File

File diff suppressed because it is too large Load Diff

1347
src/transformers/models/mpnet/modeling_tf_mpnet.py Normal file
View File

File diff suppressed because it is too large Load Diff

528
src/transformers/models/mpnet/tokenization_mpnet.py Normal file
View File

@@ -0,0 +1,528 @@
# coding=utf-8
# Copyright 2018 The HuggingFace Inc. team, Microsoft Corporation.
# Copyright (c) 2018, NVIDIA CORPORATION. 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 MPNet."""
import collections
import os
import unicodedata
from typing import List, Optional, Tuple
from ...tokenization_utils import AddedToken, PreTrainedTokenizer, _is_control, _is_punctuation, _is_whitespace
from ...utils import logging
logger = logging.get_logger(__name__)
VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"}
PRETRAINED_VOCAB_FILES_MAP = {
"vocab_file": {
"microsoft/mpnet-base": "https://huggingface.co/microsoft/mpnet-base/resolve/main/vocab.txt",
}
}
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
"microsoft/mpnet-base": 512,
}
PRETRAINED_INIT_CONFIGURATION = {
"microsoft/mpnet-base": {"do_lower_case": True},
}
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 MPNetTokenizer(PreTrainedTokenizer):
"""
This tokenizer inherits from :class:`~transformers.BertTokenizer` which contains most of the methods. Users should
refer to the superclass for more information regarding methods.
Args:
vocab_file (:obj:`str`):
Path to the vocabulary file.
do_lower_case (:obj:`bool`, `optional`, defaults to :obj:`True`):
Whether or not to lowercase the input when tokenizing.
do_basic_tokenize (:obj:`bool`, `optional`, defaults to :obj:`True`):
Whether or not to do basic tokenization before WordPiece.
never_split (:obj:`Iterable`, `optional`):
Collection of tokens which will never be split during tokenization. Only has an effect when
:obj:`do_basic_tokenize=True`
bos_token (:obj:`str`, `optional`, defaults to :obj:`"<s>"`):
The beginning of sequence token that was used during pre-training. Can be used a sequence classifier token.
.. note::
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 :obj:`cls_token`.
eos_token (:obj:`str`, `optional`, defaults to :obj:`"</s>"`):
The end of sequence token.
.. note::
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 :obj:`sep_token`.
sep_token (:obj:`str`, `optional`, defaults to :obj:`"</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 (:obj:`str`, `optional`, defaults to :obj:`"<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 (:obj:`str`, `optional`, defaults to :obj:`"[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 (:obj:`str`, `optional`, defaults to :obj:`"<pad>"`):
The token used for padding, for example when batching sequences of different lengths.
mask_token (:obj:`str`, `optional`, defaults to :obj:`"<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 (:obj:`bool`, `optional`, defaults to :obj:`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: (:obj:`bool`, `optional`):
Whether or not to strip all accents. If this option is not specified, then it will be determined by the
value for :obj:`lowercase` (as in the original BERT).
"""
vocab_files_names = VOCAB_FILES_NAMES
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
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
):
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
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(
"Can't find a vocabulary file at path '{}'. To load the vocabulary from a Google pretrained "
"model use `tokenizer = BertTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`".format(vocab_file)
)
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 MPNet sequence has the following format:
- single sequence: ``<s> X </s>``
- pair of sequences: ``<s> A </s></s> B </s>``
Args:
token_ids_0 (:obj:`List[int]`):
List of IDs to which the special tokens will be added
token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
Optional second list of IDs for sequence pairs.
Returns:
:obj:`List[int]`: list of `input IDs <../glossary.html#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 + 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`` methods.
Args:
token_ids_0 (:obj:`List[int]`):
List of ids.
token_ids_1 (:obj:`List[int]`, `optional`):
Optional second list of IDs for sequence pairs.
already_has_special_tokens (:obj:`bool`, `optional`, defaults to :obj:`False`):
Set to True if the token list is already formatted with special tokens for the model
Returns:
:obj:`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:
if token_ids_1 is not None:
raise ValueError(
"You should not supply a second sequence if the provided sequence of "
"ids is already formated with special tokens for the model."
)
return list(map(lambda x: 1 if x in [self.sep_token_id, self.cls_token_id] else 0, token_ids_0))
if token_ids_1 is None:
return [1] + ([0] * len(token_ids_0)) + [1]
return [1] + ([0] * len(token_ids_0)) + [1, 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]:
"""
Creates a mask from the two sequences passed to be used in a sequence-pair classification task. MPNet does not
make use of token type ids, therefore a list of zeros is returned.
Args:
token_ids_0 (:obj:`List[int]`):
List of ids.
token_ids_1 (:obj:`List[int]`, `optional`):
Optional second list of IDs for sequence pairs.
Returns:
:obj:`List[int]`: List of zeros.
"""
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 + sep + token_ids_1 + sep) * [0]
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(
"Saving vocabulary to {}: vocabulary indices are not consecutive."
" Please check that the vocabulary is not corrupted!".format(vocab_file)
)
index = token_index
writer.write(token + "\n")
index += 1
return (vocab_file,)
# Copied from transformers.models.bert.tokenization_bert.BasicTokenizer
class BasicTokenizer(object):
"""
Constructs a BasicTokenizer that will run basic tokenization (punctuation splitting, lower casing, etc.).
Args:
do_lower_case (:obj:`bool`, `optional`, defaults to :obj:`True`):
Whether or not to lowercase the input when tokenizing.
never_split (:obj:`Iterable`, `optional`):
Collection of tokens which will never be split during tokenization. Only has an effect when
:obj:`do_basic_tokenize=True`
tokenize_chinese_chars (:obj:`bool`, `optional`, defaults to :obj:`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: (:obj:`bool`, `optional`):
Whether or not to strip all accents. If this option is not specified, then it will be determined by the
value for :obj:`lowercase` (as in the original BERT).
"""
def __init__(self, do_lower_case=True, never_split=None, tokenize_chinese_chars=True, strip_accents=None):
if never_split is None:
never_split = []
self.do_lower_case = do_lower_case
self.never_split = set(never_split)
self.tokenize_chinese_chars = tokenize_chinese_chars
self.strip_accents = strip_accents
def tokenize(self, text, never_split=None):
"""
Basic Tokenization of a piece of text. Split on "white spaces" only, for sub-word tokenization, see
WordPieceTokenizer.
Args:
**never_split**: (`optional`) list of str
Kept for backward compatibility purposes. Now implemented directly at the base class level (see
:func:`PreTrainedTokenizer.tokenize`) List of token not to split.
"""
# union() returns a new set by concatenating the two sets.
never_split = self.never_split.union(set(never_split)) if never_split else self.never_split
text = self._clean_text(text)
# This was added on November 1st, 2018 for the multilingual and Chinese
# models. This is also applied to the English models now, but it doesn't
# matter since the English models were not trained on any Chinese data
# and generally don't have any Chinese data in them (there are Chinese
# characters in the vocabulary because Wikipedia does have some Chinese
# words in the English Wikipedia.).
if self.tokenize_chinese_chars:
text = self._tokenize_chinese_chars(text)
orig_tokens = whitespace_tokenize(text)
split_tokens = []
for token in orig_tokens:
if token not in never_split:
if self.do_lower_case:
token = token.lower()
if self.strip_accents is not False:
token = self._run_strip_accents(token)
elif self.strip_accents:
token = self._run_strip_accents(token)
split_tokens.extend(self._run_split_on_punc(token, never_split))
output_tokens = whitespace_tokenize(" ".join(split_tokens))
return output_tokens
def _run_strip_accents(self, text):
"""Strips accents from a piece of text."""
text = unicodedata.normalize("NFD", text)
output = []
for char in text:
cat = unicodedata.category(char)
if cat == "Mn":
continue
output.append(char)
return "".join(output)
def _run_split_on_punc(self, text, never_split=None):
"""Splits punctuation on a piece of text."""
if never_split is not None and text in never_split:
return [text]
chars = list(text)
i = 0
start_new_word = True
output = []
while i < len(chars):
char = chars[i]
if _is_punctuation(char):
output.append([char])
start_new_word = True
else:
if start_new_word:
output.append([])
start_new_word = False
output[-1].append(char)
i += 1
return ["".join(x) for x in output]
def _tokenize_chinese_chars(self, text):
"""Adds whitespace around any CJK character."""
output = []
for char in text:
cp = ord(char)
if self._is_chinese_char(cp):
output.append(" ")
output.append(char)
output.append(" ")
else:
output.append(char)
return "".join(output)
def _is_chinese_char(self, cp):
"""Checks whether CP is the codepoint of a CJK character."""
# This defines a "chinese character" as anything in the CJK Unicode block:
# https://en.wikipedia.org/wiki/CJK_Unified_Ideographs_(Unicode_block)
#
# Note that the CJK Unicode block is NOT all Japanese and Korean characters,
# despite its name. The modern Korean Hangul alphabet is a different block,
# as is Japanese Hiragana and Katakana. Those alphabets are used to write
# space-separated words, so they are not treated specially and handled
# like the all of the other languages.
if (
(cp >= 0x4E00 and cp <= 0x9FFF)
or (cp >= 0x3400 and cp <= 0x4DBF) #
or (cp >= 0x20000 and cp <= 0x2A6DF) #
or (cp >= 0x2A700 and cp <= 0x2B73F) #
or (cp >= 0x2B740 and cp <= 0x2B81F) #
or (cp >= 0x2B820 and cp <= 0x2CEAF) #
or (cp >= 0xF900 and cp <= 0xFAFF)
or (cp >= 0x2F800 and cp <= 0x2FA1F) #
): #
return True
return False
def _clean_text(self, text):
"""Performs invalid character removal and whitespace cleanup on text."""
output = []
for char in text:
cp = ord(char)
if cp == 0 or cp == 0xFFFD or _is_control(char):
continue
if _is_whitespace(char):
output.append(" ")
else:
output.append(char)
return "".join(output)
# Copied from transformers.models.bert.tokenization_bert.WordpieceTokenizer
class WordpieceTokenizer(object):
"""Runs WordPiece tokenization."""
def __init__(self, vocab, unk_token, max_input_chars_per_word=100):
self.vocab = vocab
self.unk_token = unk_token
self.max_input_chars_per_word = max_input_chars_per_word
def tokenize(self, text):
"""
Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform
tokenization using the given vocabulary.
For example, :obj:`input = "unaffable"` wil return as output :obj:`["un", "##aff", "##able"]`.
Args:
text: A single token or whitespace separated tokens. This should have
already been passed through `BasicTokenizer`.
Returns:
A list of wordpiece tokens.
"""
output_tokens = []
for token in whitespace_tokenize(text):
chars = list(token)
if len(chars) > self.max_input_chars_per_word:
output_tokens.append(self.unk_token)
continue
is_bad = False
start = 0
sub_tokens = []
while start < len(chars):
end = len(chars)
cur_substr = None
while start < end:
substr = "".join(chars[start:end])
if start > 0:
substr = "##" + substr
if substr in self.vocab:
cur_substr = substr
break
end -= 1
if cur_substr is None:
is_bad = True
break
sub_tokens.append(cur_substr)
start = end
if is_bad:
output_tokens.append(self.unk_token)
else:
output_tokens.extend(sub_tokens)
return output_tokens

208
src/transformers/models/mpnet/tokenization_mpnet_fast.py Normal file
View File

@@ -0,0 +1,208 @@
# coding=utf-8
# Copyright 2018 The HuggingFace Inc. team, Microsoft Corporation.
# Copyright (c) 2018, NVIDIA CORPORATION. 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.
"""Fast Tokenization classes for MPNet."""
import json
from typing import List, Optional, Tuple
from tokenizers import normalizers
from ...tokenization_utils import AddedToken
from ...tokenization_utils_fast import PreTrainedTokenizerFast
from ...utils import logging
from .tokenization_mpnet import MPNetTokenizer
logger = logging.get_logger(__name__)
VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"}
PRETRAINED_VOCAB_FILES_MAP = {
"vocab_file": {
"microsoft/mpnet-base": "https://huggingface.co/microsoft/mpnet-base/resolve/main/vocab.txt",
},
"tokenizer_file": {
"microsoft/mpnet-base": "https://huggingface.co/microsoft/mpnet-base/resolve/main/tokenizer.json",
},
}
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
"microsoft/mpnet-base": 512,
}
PRETRAINED_INIT_CONFIGURATION = {
"microsoft/mpnet-base": {"do_lower_case": True},
}
class MPNetTokenizerFast(PreTrainedTokenizerFast):
r"""
Construct a "fast" MPNet tokenizer (backed by HuggingFace's `tokenizers` library). Based on WordPiece.
This tokenizer inherits from :class:`~transformers.PreTrainedTokenizerFast` which contains most of the main
methods. Users should refer to this superclass for more information regarding those methods.
Args:
vocab_file (:obj:`str`):
File containing the vocabulary.
do_lower_case (:obj:`bool`, `optional`, defaults to :obj:`True`):
Whether or not to lowercase the input when tokenizing.
bos_token (:obj:`str`, `optional`, defaults to :obj:`"<s>"`):
The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
.. note::
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 :obj:`cls_token`.
eos_token (:obj:`str`, `optional`, defaults to :obj:`"</s>"`):
The end of sequence token.
.. note::
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 :obj:`sep_token`.
sep_token (:obj:`str`, `optional`, defaults to :obj:`"</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 (:obj:`str`, `optional`, defaults to :obj:`"<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 (:obj:`str`, `optional`, defaults to :obj:`"[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 (:obj:`str`, `optional`, defaults to :obj:`"<pad>"`):
The token used for padding, for example when batching sequences of different lengths.
mask_token (:obj:`str`, `optional`, defaults to :obj:`"<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 (:obj:`bool`, `optional`, defaults to :obj:`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: (:obj:`bool`, `optional`):
Whether or not to strip all accents. If this option is not specified, then it will be determined by the
value for :obj:`lowercase` (as in the original BERT).
"""
vocab_files_names = VOCAB_FILES_NAMES
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
slow_tokenizer_class = MPNetTokenizer
def __init__(
self,
vocab_file,
tokenizer_file=None,
do_lower_case=True,
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__(
vocab_file,
tokenizer_file=tokenizer_file,
do_lower_case=do_lower_case,
bos_token=bos_token,
eos_token=eos_token,
sep_token=sep_token,
cls_token=cls_token,
unk_token=unk_token,
pad_token=pad_token,
mask_token=mask_token,
tokenize_chinese_chars=tokenize_chinese_chars,
strip_accents=strip_accents,
**kwargs,
)
pre_tok_state = json.loads(self.backend_tokenizer.normalizer.__getstate__())
if (
pre_tok_state.get("do_lower_case", do_lower_case) != do_lower_case
or pre_tok_state.get("strip_accents", strip_accents) != strip_accents
):
pre_tok_class = getattr(normalizers, pre_tok_state.pop("type"))
pre_tok_state["do_lower_case"] = do_lower_case
pre_tok_state["strip_accents"] = strip_accents
self.backend_tokenizer.normalizer = pre_tok_class(**pre_tok_state)
self.do_lower_case = do_lower_case
@property
def mask_token(self) -> str:
"""
:obj:`str`: Mask token, to use when training a model with masked-language modeling. Log an error if used while
not having been set.
MPNet tokenizer has a special mask token to be usble in the fill-mask pipeline. The mask token will greedily
comprise the space before the `<mask>`.
"""
if self._mask_token is None and self.verbose:
logger.error("Using mask_token, but it is not set yet.")
return None
return str(self._mask_token)
@mask_token.setter
def mask_token(self, value):
"""
Overriding the default behavior of the mask token to have it eat the space before it.
This is needed to preserve backward compatibility with all the previously used models based on MPNet.
"""
# Mask token behave like a normal word, i.e. include the space before it
# So we set lstrip to True
value = AddedToken(value, lstrip=True, rstrip=False) if isinstance(value, str) else value
self._mask_token = value
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
output = [self.bos_token_id] + token_ids_0 + [self.eos_token_id]
if token_ids_1 is None:
return output
return output + [self.eos_token_id] + token_ids_1 + [self.eos_token_id]
def create_token_type_ids_from_sequences(
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
) -> List[int]:
"""
Creates a mask from the two sequences passed to be used in a sequence-pair classification task. MPNet does not
make use of token type ids, therefore a list of zeros is returned
Args:
token_ids_0 (:obj:`List[int]`):
List of ids.
token_ids_1 (:obj:`List[int]`, `optional`):
Optional second list of IDs for sequence pairs
Returns:
:obj:`List[int]`: List of zeros.
"""
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 + sep + token_ids_1 + sep) * [0]
def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
files = self._tokenizer.model.save(save_directory, name=filename_prefix)
return tuple(files)