You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
182 lines
7.0 KiB
182 lines
7.0 KiB
# Copyright 2021 The Facebook Inc. and The HuggingFace Inc. 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 class for Blenderbot."""
|
|
|
|
from tokenizers import Tokenizer, decoders, pre_tokenizers, processors
|
|
from tokenizers.models import BPE
|
|
|
|
from ...tokenization_utils_base import AddedToken
|
|
from ...tokenization_utils_tokenizers import TokenizersBackend
|
|
from ...utils import logging
|
|
|
|
|
|
logger = logging.get_logger(__name__)
|
|
|
|
|
|
VOCAB_FILES_NAMES = {
|
|
"vocab_file": "vocab.json",
|
|
"merges_file": "merges.txt",
|
|
"tokenizer_config_file": "tokenizer_config.json",
|
|
}
|
|
|
|
|
|
class BlenderbotTokenizer(TokenizersBackend):
|
|
"""
|
|
Construct a "fast" Blenderbot tokenizer (backed by HuggingFace's *tokenizers* library), derived from the GPT-2
|
|
tokenizer, using 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 BlenderbotTokenizerFast
|
|
|
|
>>> tokenizer = BlenderbotTokenizerFast.from_pretrained("facebook/blenderbot-3B")
|
|
>>> tokenizer("Hello world")["input_ids"]
|
|
[6950, 1085, 2]
|
|
|
|
>>> tokenizer(" Hello world")["input_ids"]
|
|
[6950, 1085, 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.
|
|
|
|
<Tip>
|
|
|
|
When used with `is_split_into_words=True`, this tokenizer needs to be instantiated with `add_prefix_space=True`.
|
|
|
|
</Tip>
|
|
|
|
This tokenizer inherits from [`PreTrainedTokenizerFast`] which contains most of the main methods. Users should
|
|
refer to this superclass for more information regarding those methods.
|
|
|
|
Args:
|
|
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.
|
|
add_prefix_space (`bool`, *optional*, defaults to `True`):
|
|
Whether or not to add an initial space to the input. This allows to treat the leading word just as any
|
|
other word. (Blenderbot tokenizer detect beginning of words by the preceding space).
|
|
vocab (`str` or `dict[str, int]`, *optional*):
|
|
Custom vocabulary dictionary. If not provided, vocabulary is loaded from `vocab_file`.
|
|
merges (`str` or `list[str]`, *optional*):
|
|
Custom merges list. If not provided, merges are loaded from `merges_file`.
|
|
"""
|
|
|
|
vocab_files_names = VOCAB_FILES_NAMES
|
|
model_input_names = ["input_ids", "attention_mask"]
|
|
model = BPE
|
|
|
|
def __init__(
|
|
self,
|
|
bos_token="<s>",
|
|
eos_token="</s>",
|
|
sep_token="</s>",
|
|
cls_token="<s>",
|
|
unk_token="<unk>",
|
|
pad_token="<pad>",
|
|
mask_token="<mask>",
|
|
add_prefix_space=True,
|
|
vocab=None,
|
|
merges=None,
|
|
**kwargs,
|
|
):
|
|
self.add_prefix_space = add_prefix_space
|
|
mask_token = (
|
|
AddedToken(mask_token, lstrip=True, rstrip=False, normalized=False)
|
|
if isinstance(mask_token, str)
|
|
else mask_token
|
|
)
|
|
|
|
# Initialize vocab and merges; when not provided fall back to minimal vocab
|
|
self._vocab = (
|
|
vocab
|
|
if vocab is not None
|
|
else {
|
|
str(bos_token): 0,
|
|
str(pad_token): 1,
|
|
str(eos_token): 2,
|
|
str(unk_token): 3,
|
|
str(mask_token): 4,
|
|
}
|
|
)
|
|
|
|
self._merges = merges or []
|
|
self._tokenizer = Tokenizer(
|
|
BPE(
|
|
vocab=self._vocab,
|
|
merges=self._merges,
|
|
dropout=None,
|
|
continuing_subword_prefix="",
|
|
end_of_word_suffix="",
|
|
fuse_unk=False,
|
|
)
|
|
)
|
|
|
|
self._tokenizer.pre_tokenizer = pre_tokenizers.ByteLevel(add_prefix_space=add_prefix_space)
|
|
self._tokenizer.decoder = decoders.ByteLevel()
|
|
super().__init__(
|
|
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,
|
|
add_prefix_space=add_prefix_space,
|
|
**kwargs,
|
|
)
|
|
self._tokenizer.post_processor = processors.RobertaProcessing(
|
|
sep=(str(eos_token), self.eos_token_id),
|
|
cls=(str(bos_token), self.bos_token_id),
|
|
add_prefix_space=add_prefix_space,
|
|
trim_offsets=True,
|
|
)
|
|
|
|
|
|
__all__ = ["BlenderbotTokenizer"]
|