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.
133 lines
5.2 KiB
133 lines
5.2 KiB
# 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 OpenAI GPT."""
|
|
|
|
from tokenizers import Tokenizer, decoders, pre_tokenizers
|
|
from tokenizers.models import BPE
|
|
|
|
from ...tokenization_utils_tokenizers import AddedToken, TokenizersBackend
|
|
from ...utils import logging
|
|
|
|
|
|
logger = logging.get_logger(__name__)
|
|
|
|
VOCAB_FILES_NAMES = {
|
|
"vocab_file": "vocab.json",
|
|
"merges_file": "merges.txt",
|
|
}
|
|
|
|
|
|
class GPT2Tokenizer(TokenizersBackend):
|
|
"""
|
|
Construct a GPT-2 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 GPT2Tokenizer
|
|
|
|
>>> tokenizer = GPT2Tokenizer.from_pretrained("openai-community/gpt2")
|
|
>>> tokenizer("Hello world")["input_ids"]
|
|
[15496, 995]
|
|
|
|
>>> tokenizer(" Hello world")["input_ids"]
|
|
[18435, 995]
|
|
```
|
|
|
|
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 will add a space before each word (even the first one).
|
|
|
|
</Tip>
|
|
|
|
This tokenizer inherits from [`TokenizersBackend`] 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.
|
|
unk_token (`str`, *optional*, defaults to `"<|endoftext|>"`):
|
|
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.
|
|
bos_token (`str`, *optional*, defaults to `"<|endoftext|>"`):
|
|
The beginning of sequence token.
|
|
eos_token (`str`, *optional*, defaults to `"<|endoftext|>"`):
|
|
The end of sequence token.
|
|
pad_token (`str`, *optional*):
|
|
The token used for padding, for example when batching sequences of different lengths.
|
|
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. (GPT2 tokenizer detect beginning of words by the preceding space).
|
|
add_bos_token (`bool`, *optional*, defaults to `False`):
|
|
Whether or not to add an initial beginning of sentence token to the input. This allows to treat the leading
|
|
word just as any other word.
|
|
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,
|
|
vocab: str | dict[str, int] | None = None,
|
|
merges: str | list[str] | None = None,
|
|
errors: str = "replace",
|
|
unk_token: AddedToken | str = "<|endoftext|>",
|
|
bos_token: AddedToken | str = "<|endoftext|>",
|
|
eos_token: AddedToken | str = "<|endoftext|>",
|
|
pad_token: AddedToken | str | None = None,
|
|
add_prefix_space=False,
|
|
**kwargs,
|
|
):
|
|
self.add_prefix_space = add_prefix_space
|
|
self._vocab = vocab if vocab is not None else {}
|
|
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__(
|
|
errors=errors,
|
|
unk_token=unk_token,
|
|
bos_token=bos_token,
|
|
eos_token=eos_token,
|
|
pad_token=pad_token,
|
|
add_prefix_space=add_prefix_space,
|
|
**kwargs,
|
|
)
|
|
|
|
|
|
__all__ = ["GPT2Tokenizer"]
|