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.
102 lines
3.2 KiB
102 lines
3.2 KiB
# 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 tokenizers import AddedToken, Regex, Tokenizer, decoders, normalizers, pre_tokenizers
|
|
from tokenizers.models import BPE
|
|
|
|
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_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+"""
|
|
|
|
|
|
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,
|
|
**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])
|
|
|
|
|
|
__all__ = ["Qwen2Tokenizer"]
|