# 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.
# ============================================================================
"""GPT2 Tokenizer"""
import json
from functools import lru_cache
from typing import List, Optional
import os
import regex as re
from mindformers.tools.register import MindFormerRegister, MindFormerModuleType
from mindformers.models.base_tokenizer import Tokenizer, AddedToken
from mindformers.tools import logger
from ...mindformer_book import MindFormerBook
__all__ = ['GPT2Tokenizer']
@lru_cache()
def bytes_to_unicode():
"""
Returns list of utf-8 byte and a mapping to unicode strings. We specifically avoids mapping to whitespace/control
characters the bpe code barfs on.
The reversible bpe codes work on unicode strings. This means you need a large # of unicode characters in your vocab
if you want to avoid UNKs. When you're at something like a 10B token dataset you end up needing around 5K for
decent coverage. This is a significant percentage of your normal, say, 32K bpe vocab. To avoid that, we want lookup
tables between utf-8 bytes and unicode strings.
"""
bs = (
list(range(ord("!"), ord("~") + 1)) + list(range(ord("¡"), ord("¬") + 1)) + list(range(ord("®"), ord("ÿ") + 1))
)
cs = bs[:]
n = 0
for b in range(2**8):
if b not in bs:
bs.append(b)
cs.append(2**8 + n)
n += 1
cs = [chr(n) for n in cs]
return dict(zip(bs, cs))
def get_pairs(word):
"""
Return set of symbol pairs in a word.
Word is represented as tuple of symbols (symbols being variable-length strings).
"""
pairs = set()
prev_char = word[0]
for char in word[1:]:
pairs.add((prev_char, char))
prev_char = char
return pairs
VOCAB_FILES_NAMES = {
"vocab_file": "vocab.json",
"merges_file": "merges.txt",
}
[文档]@MindFormerRegister.register(MindFormerModuleType.TOKENIZER)
class GPT2Tokenizer(Tokenizer):
"""
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 mindformers import GPT2Tokenizer
>>> tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
>>> tokenizer("Hello world", add_bos_token=False, add_eos_token=False)["input_ids"]
[15496, 995]
>>> tokenizer(" Hello world", add_bos_token=False, add_eos_token=False)["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 [`PreTrainedTokenizer`] 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.
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 `True`):
Whether or not to add the bos_token_id to the left of the input.
add_eos_token(`bool`, *optional*, defaults to `True`):
Whether or not to add the eos_token_id to the right of the input.
Examples:
>>> from mindformers import GPT2Tokenizer
>>> tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
>>> res = tokenizer("Hello world")
>>> print(res)
{'input_ids': [50256, 15496, 995, 50256], 'token_type_ids': [0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1]}
>>> tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
>>> res = tokenizer("Hello world", add_special_tokens=False)
>>> print(res)
{'input_ids': [15496, 995], 'token_type_ids': [0, 0], 'attention_mask': [1, 1]}
Outputs:
A dict contains the processed ids, attention_mask that specific by the member `MODEL_INPUT_NAME`
of the subclass.
"""
vocab_files_names = VOCAB_FILES_NAMES
model_input_names = ["input_ids", "token_type_ids", "attention_mask"]
FILE_LIST = ['tokenizer_config.json']
_support_list = MindFormerBook.get_tokenizer_support_list()['gpt2']
def __init__(
self,
vocab_file,
merges_file,
errors="replace",
unk_token="<|endoftext|>",
bos_token="<|endoftext|>",
eos_token="<|endoftext|>",
pad_token="<|endoftext|>",
add_prefix_space=False,
add_bos_token=False,
add_eos_token=False,
**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
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
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,
)
self.add_bos_token = add_bos_token
self.add_eos_token = add_eos_token
with open(vocab_file, encoding="utf-8") as vocab_handle:
self.encoder = json.load(vocab_handle)
self.decoder = {v: k for k, v in self.encoder.items()}
self.errors = errors # how to handle errors in decoding
self.byte_encoder = bytes_to_unicode()
self.byte_decoder = {v: k for k, v in self.byte_encoder.items()}
with open(merges_file, encoding="utf-8") as merges_handle:
bpe_merges = merges_handle.read().split("\n")[1:-1]
bpe_merges = [tuple(merge.split()) for merge in bpe_merges]
self.bpe_ranks = dict(zip(bpe_merges, range(len(bpe_merges))))
self.cache = {}
self.add_prefix_space = add_prefix_space
# Should have added re.IGNORECASE so BPE merges can happen for capitalized versions of contractions
self.pat = re.compile(r"""'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+""")
@property
def vocab_size(self):
return len(self.encoder)
def get_vocab(self):
return dict(self.encoder, **self.added_tokens_encoder)
[文档] def bpe(self, token):
"""bpe encode """
if token in self.cache:
return self.cache[token]
word = tuple(token)
pairs = get_pairs(word)
if not pairs:
return token
while True:
bigram = min(pairs, key=lambda pair: self.bpe_ranks.get(pair, float("inf")))
if bigram not in self.bpe_ranks:
break
first, second = bigram
new_word = []
i = 0
while i < len(word):
try:
j = word.index(first, i)
except ValueError:
new_word.extend(word[i:])
break
else:
new_word.extend(word[i:j])
i = j
if word[i] == first and i < len(word) - 1 and word[i + 1] == second:
new_word.append(first + second)
i += 2
else:
new_word.append(word[i])
i += 1
new_word = tuple(new_word)
word = new_word
if len(word) == 1:
break
else:
pairs = get_pairs(word)
word = " ".join(word)
self.cache[token] = word
return word
[文档] 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` or `encode_plus` methods.
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 not self.add_bos_token:
return super().get_special_tokens_mask(
token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=False
)
if token_ids_1 is None:
return [1] + ([0] * len(token_ids_0))
return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1))
def _tokenize(self, text, **kwargs):
"""Tokenize a string."""
bpe_tokens = []
for token in re.findall(self.pat, text):
token = "".join(
self.byte_encoder[b] for b in token.encode("utf-8")
) # Maps all our bytes to unicode strings, avoiding control tokens of the BPE (spaces in our case)
bpe_tokens.extend(bpe_token for bpe_token in self.bpe(token).split(" "))
return bpe_tokens
def _convert_token_to_id(self, token):
"""Converts a token (str) in an id using the vocab."""
return self.encoder.get(token, self.encoder.get(self.unk_token))
def _convert_id_to_token(self, index):
"""Converts an index (integer) in a token (str) using the vocab."""
return self.decoder.get(index)
[文档] def convert_tokens_to_string(self, tokens):
"""Converts a sequence of tokens (string) in a single string."""
text = "".join(tokens)
text = bytearray([self.byte_decoder[c] for c in text]).decode("utf-8", errors=self.errors)
return text
[文档] def save_vocabulary(self, save_directory, filename_prefix=None):
"""write the word to the files"""
if not os.path.isdir(save_directory):
logger.error("Vocabulary path (%s) should be a directory", save_directory)
return None
vocab_file = os.path.join(
save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
)
merge_file = os.path.join(
save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["merges_file"]
)
with open(vocab_file, "w", encoding="utf-8") as f:
# you can set sort_keys=True, then the keys of vocabulary dict is sorted,
# which is different from original vocabulary file.
f.write(json.dumps(self.encoder, indent=2, ensure_ascii=False) + "\n")
index = 0
with open(merge_file, "w", encoding="utf-8") as writer:
writer.write("#version: 0.2\n")
for bpe_tokens, token_index in sorted(self.bpe_ranks.items(), key=lambda kv: kv[1]):
if index != token_index:
logger.warning(
"Saving vocabulary to %s: BPE merge indices are not consecutive."
" Please check that the tokenizer is not corrupted!", merge_file
)
index = token_index
writer.write(" ".join(bpe_tokens) + "\n")
index += 1
return vocab_file, merge_file
def prepare_for_tokenization(self, text, **kwargs):
add_prefix_space = kwargs.pop("add_prefix_space", self.add_prefix_space)
is_split_into_words = kwargs.pop("is_split_into_words", False)
if is_split_into_words or add_prefix_space:
text = " " + text
return (text, kwargs)
[文档] 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. An ALBERT
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, 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).
"""
bos_token_id = [self.bos_token_id] if self.add_bos_token else []
eos_token_id = [self.eos_token_id] if self.add_eos_token else []
output = [0] * len(bos_token_id + token_ids_0 + eos_token_id)
if token_ids_1 is not None:
output += [1] * len(bos_token_id + token_ids_1 + eos_token_id)
return output