File size: 12,337 Bytes
700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 15b8cd7 700ae47 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 | # Copyright 2024 The Qwen team, Alibaba Group 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 classes for Qwen2."""
from typing import List, Optional
from tokenizers import AddedToken, Regex, Tokenizer, decoders, normalizers, pre_tokenizers
from tokenizers.models import BPE
from tokenizers.processors import TemplateProcessing
VOCAB_FILES_NAMES = {
"vocab_file": "vocab.json",
"merges_file": "merges.txt",
"tokenizer_file": "tokenizer.json",
}
MAX_MODEL_INPUT_SIZES = {"qwen/qwen-tokenizer": 32768}
PRETOKENIZE_REGEX = r"""(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"""
from packaging.version import Version
import transformers
if Version(transformers.__version__) >= Version("5.0.0"):
from transformers import TokenizersBackend
class Qwen2Tokenizer(TokenizersBackend):
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,
unk_token: str = "<|endoftext|>",
bos_token=None,
eos_token: str = "<|endoftext|>",
pad_token: str = "<|endoftext|>",
add_prefix_space=None,
add_eos_token=True,
**kwargs,
):
self.add_prefix_space = add_prefix_space if add_prefix_space is not None else False
self._vocab = (
vocab
if vocab is not None
else {
"<|endoftext|>": 0,
}
)
self._merges = merges or []
self._tokenizer = Tokenizer(
BPE(
vocab=self._vocab,
merges=self._merges,
dropout=None,
unk_token=None,
continuing_subword_prefix="",
end_of_word_suffix="",
fuse_unk=False,
byte_fallback=False,
)
)
self._tokenizer.decoder = decoders.ByteLevel()
self._tokenizer.normalizer = normalizers.NFC()
self._tokenizer.pre_tokenizer = pre_tokenizers.Sequence(
[
pre_tokenizers.Split(
Regex(PRETOKENIZE_REGEX),
behavior="isolated",
invert=False,
),
pre_tokenizers.ByteLevel(
add_prefix_space=self.add_prefix_space,
use_regex=False,
),
]
)
super().__init__(
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_tokens([AddedToken(token, special=True) for token in self.all_special_tokens])
self._add_eos_token = add_eos_token
self.update_post_processor()
@property
def add_eos_token(self):
return self._add_eos_token
def update_post_processor(self):
eos = self.eos_token
eos_token_id = self.eos_token_id
if eos is None and self.add_eos_token:
raise ValueError("add_eos_token = True but eos_token = None")
single = f"$A:0{(' ' + eos + ':0') if self.add_eos_token else ''}"
pair = f"{single} $B:1{(' ' + eos + ':1') if self.add_eos_token else ''}"
special_tokens = []
if self.add_eos_token:
special_tokens.append((eos, eos_token_id))
self._tokenizer.post_processor = TemplateProcessing(
single=single, pair=pair, special_tokens=special_tokens
)
else:
from transformers.models.qwen2.tokenization_qwen2 import Qwen2Tokenizer as OriginalQwen2Tokenizer
class Qwen2Tokenizer(OriginalQwen2Tokenizer):
"""
Construct a Qwen2 tokenizer. Based on byte-level Byte-Pair-Encoding.
Same with GPT2Tokenizer, this tokenizer has been trained to treat spaces like parts of the tokens so a word will
be encoded differently whether it is at the beginning of the sentence (without space) or not:
```python
>>> from transformers import Qwen2Tokenizer
>>> tokenizer = Qwen2Tokenizer.from_pretrained("Qwen/Qwen-tokenizer")
>>> tokenizer("Hello world")["input_ids"]
[9707, 1879]
>>> tokenizer(" Hello world")["input_ids"]
[21927, 1879]
```
This is expected.
You should not use GPT2Tokenizer instead, because of the different pretokenization rules.
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*):
The beginning of sequence token. Not applicable for this tokenizer.
eos_token (`str`, *optional*, defaults to `"<|endoftext|>"`):
The end of sequence token.
pad_token (`str`, *optional*, defaults to `"<|endoftext|>"`):
The token used for padding, for example when batching sequences of different lengths.
clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`):
Whether or not the model should cleanup the spaces that were added when splitting the input text during the
tokenization process. Not applicable to this tokenizer, since tokenization does not add spaces.
split_special_tokens (`bool`, *optional*, defaults to `False`):
Whether or not the special tokens should be split during the tokenization process. The default behavior is
to not split special tokens. This means that if `<|endoftext|>` is the `eos_token`, then `tokenizer.tokenize("<|endoftext|>") =
['<|endoftext|>`]. Otherwise, if `split_special_tokens=True`, then `tokenizer.tokenize("<|endoftext|>")` will be give `['<',
'|', 'endo', 'ft', 'ext', '|', '>']`. This argument is only supported for `slow` tokenizers for the moment.
add_eos_token (`bool`, *optional*, defaults to `False`):
Whether or not to add an `eos_token` at the end of sequences.
"""
def __init__(
self,
vocab_file,
merges_file,
errors="replace",
unk_token="<|endoftext|>",
bos_token=None,
eos_token="<|endoftext|>",
pad_token="<|endoftext|>",
clean_up_tokenization_spaces=False,
split_special_tokens=False,
add_eos_token=False,
**kwargs,
):
# The add_eos_token code was inspired by the LlamaTokenizer
self.add_eos_token = add_eos_token
super().__init__(
vocab_file=vocab_file,
merges_file=merges_file,
errors=errors,
unk_token=unk_token,
bos_token=bos_token,
eos_token=eos_token,
pad_token=pad_token,
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
split_special_tokens=split_special_tokens,
add_eos_token=add_eos_token,
**kwargs,
)
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
eos_token_id = [self.eos_token_id] if self.add_eos_token else []
output = token_ids_0 + eos_token_id
if token_ids_1 is not None:
output = output + token_ids_1 + eos_token_id
return output
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]:
"""
Retrieve 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` method.
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
)
eos_token_id = [1] if self.add_eos_token else []
if token_ids_1 is None:
return ([0] * len(token_ids_0)) + eos_token_id
return (
([0] * len(token_ids_0))
+ eos_token_id
+ ([0] * len(token_ids_1))
+ 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. 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).
"""
eos_token_id = [self.eos_token_id] if self.add_eos_token else []
output = [0] * len(token_ids_0 + eos_token_id)
if token_ids_1 is not None:
output += [1] * len(token_ids_1 + eos_token_id)
return output
__all__ = ["Qwen2Tokenizer"]
|