# coding=utf-8
# Copyright 2018 The Open AI Team Authors 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 classes for RoBERTa."""
import logging
from tokenizers.processors import RobertaProcessing
from .tokenization_gpt2 import GPT2Tokenizer, GPT2TokenizerFast
logger = logging.getLogger(__name__)
VOCAB_FILES_NAMES = {
"vocab_file": "vocab.json",
"merges_file": "merges.txt",
}
PRETRAINED_VOCAB_FILES_MAP = {
"vocab_file": {
"roberta-base": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-vocab.json",
"roberta-large": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-vocab.json",
"roberta-large-mnli": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-mnli-vocab.json",
"distilroberta-base": "https://s3.amazonaws.com/models.huggingface.co/bert/distilroberta-base-vocab.json",
"roberta-base-openai-detector": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-vocab.json",
"roberta-large-openai-detector": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-vocab.json",
},
"merges_file": {
"roberta-base": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-merges.txt",
"roberta-large": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-merges.txt",
"roberta-large-mnli": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-mnli-merges.txt",
"distilroberta-base": "https://s3.amazonaws.com/models.huggingface.co/bert/distilroberta-base-merges.txt",
"roberta-base-openai-detector": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-merges.txt",
"roberta-large-openai-detector": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-merges.txt",
},
}
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
"roberta-base": 512,
"roberta-large": 512,
"roberta-large-mnli": 512,
"distilroberta-base": 512,
"roberta-base-openai-detector": 512,
"roberta-large-openai-detector": 512,
}
[docs]class RobertaTokenizer(GPT2Tokenizer):
"""
RoBERTa BPE tokenizer, derived from the GPT-2 tokenizer. Peculiarities:
- Byte-level Byte-Pair-Encoding
- Requires a space to start the input string => the encoding methods should be called with the
``add_prefix_space`` flag set to ``True``.
Otherwise, this tokenizer ``encode`` and ``decode`` method will not conserve
the absence of a space at the beginning of a string: `tokenizer.decode(tokenizer.encode("Hello")) = " Hello"`
"""
vocab_files_names = VOCAB_FILES_NAMES
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
def __init__(
self,
vocab_file,
merges_file,
errors="replace",
bos_token="<s>",
eos_token="</s>",
sep_token="</s>",
cls_token="<s>",
unk_token="<unk>",
pad_token="<pad>",
mask_token="<mask>",
**kwargs
):
super().__init__(
vocab_file=vocab_file,
merges_file=merges_file,
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,
**kwargs,
)
self.max_len_single_sentence = self.max_len - 2 # take into account special tokens
self.max_len_sentences_pair = self.max_len - 4 # take into account special tokens
[docs] def get_special_tokens_mask(self, token_ids_0, token_ids_1=None, already_has_special_tokens=False):
"""
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 of ids (must not contain special tokens)
token_ids_1: Optional list of ids (must not contain special tokens), necessary when fetching sequence ids
for sequence pairs
already_has_special_tokens: (default False) Set to True if the token list is already formated with
special tokens for the model
Returns:
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]
[docs] def create_token_type_ids_from_sequences(self, token_ids_0, token_ids_1=None):
"""
Creates a mask from the two sequences passed to be used in a sequence-pair classification task.
RoBERTa does not make use of token type ids, therefore a list of zeros is returned.
if token_ids_1 is None, only returns the first portion of the mask (0'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 + sep + token_ids_1 + sep) * [0]
[docs] def prepare_for_tokenization(self, text, add_special_tokens=False, **kwargs):
if "add_prefix_space" in kwargs:
add_prefix_space = kwargs["add_prefix_space"]
else:
add_prefix_space = add_special_tokens
if add_prefix_space and not text[0].isspace():
text = " " + text
return text
class RobertaTokenizerFast(GPT2TokenizerFast):
vocab_files_names = VOCAB_FILES_NAMES
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
def __init__(
self,
vocab_file,
merges_file,
errors="replace",
bos_token="<s>",
eos_token="</s>",
sep_token="</s>",
cls_token="<s>",
unk_token="<unk>",
pad_token="<pad>",
mask_token="<mask>",
add_prefix_space=False,
**kwargs
):
kwargs.setdefault("pad_token", pad_token)
kwargs.setdefault("sep_token", sep_token)
kwargs.setdefault("cls_token", cls_token)
kwargs.setdefault("mask_token", mask_token)
super().__init__(
vocab_file=vocab_file,
merges_file=merges_file,
unk_token=unk_token,
bos_token=bos_token,
eos_token=eos_token,
add_prefix_space=add_prefix_space,
**kwargs,
)
self.tokenizer._tokenizer.post_processor = RobertaProcessing(
(sep_token, self.sep_token_id), (cls_token, self.cls_token_id)
)
# As we override the post_processor post super.__init__ the computed num_added_tokens is wrong in super().
# We need to recompute max_len according to the newly register post_processor to get real values.
self.max_len_single_sentence = self.max_len - self.num_added_tokens(False) # take into account special tokens
self.max_len_sentences_pair = self.max_len - self.num_added_tokens(True) # take into account special tokens