File size: 8,095 Bytes
580a183 af9914c 580a183 af9914c 580a183 af9914c 580a183 af9914c 580a183 |
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 |
# Copyright (c) Alibaba Cloud.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
"""Tokenization classes for QWen."""
from __future__ import absolute_import, division, print_function, unicode_literals
import json
import logging
import os
import unicodedata
from io import open
import base64
import tiktoken
from typing import List, Optional, Tuple, Union
from transformers import PreTrainedTokenizer, AddedToken
logger = logging.getLogger(__name__)
VOCAB_FILES_NAMES = {"vocab_file": "qwen.tiktoken"}
class QWenTokenizer(PreTrainedTokenizer):
"""QWen tokenizer."""
"""NOTE: This tokenizer will not handle special tokens to avoid injection attacks"""
vocab_files_names = VOCAB_FILES_NAMES
def __init__(
self,
vocab_file,
errors="replace",
max_len=None,
unk_token="<|endoftext|>",
bos_token="<|endoftext|>",
eos_token="<|endoftext|>",
pad_token=None,
add_prefix_space=False,
add_bos_token=False,
add_more_sp_tokens=True,
**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,
add_bos_token=add_bos_token,
)
self.add_bos_token = add_bos_token
self.max_len = max_len if max_len is not None else int(1e12)
self.errors = errors # how to handle errors in decoding
name = "QWen"
ENDOFTEXT = "<|endoftext|>"
IMSTART = "<|im_start|>"
IMEND = "<|im_end|>"
if add_more_sp_tokens:
special_tokens = (
ENDOFTEXT,
IMSTART,
IMEND,
"<R>",
"<S>",
"<X>",
"<mask>",
"<sep>",
) + tuple([f"<extra_{i}>" for i in range(200)])
else:
special_tokens = (ENDOFTEXT, IMSTART, IMEND)
PAT_STR = 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+"""
def load_tiktoken_bpe(tiktoken_bpe_file: str) -> "dict[bytes, int]":
contents = open(tiktoken_bpe_file, "rb").read()
return {
base64.b64decode(token): int(rank)
for token, rank in (
line.split() for line in contents.splitlines() if line
)
}
mergeable_ranks = load_tiktoken_bpe(vocab_file)
special_tokens = {
token: index
for index, token in enumerate(special_tokens, start=len(mergeable_ranks))
}
self.special_tokens = special_tokens
enc = tiktoken.Encoding(
name,
pat_str=PAT_STR,
mergeable_ranks=mergeable_ranks,
special_tokens=special_tokens,
)
assert (
len(mergeable_ranks) + len(special_tokens) == enc.n_vocab
), f"{len(mergeable_ranks) + len(special_tokens)} != {enc.n_vocab} in encoding"
self.mergeable_ranks = mergeable_ranks
self.encoder = self.mergeable_ranks
self.decoder = {v: k for k, v in self.encoder.items()}
self.tokenizer = enc # type: tiktoken.Encoding
self.eod_id = self.tokenizer.eot_token
self.im_start_id = special_tokens[IMSTART]
self.im_end_id = special_tokens[IMEND]
def __len__(self):
return self.tokenizer.n_vocab
def get_vocab(self):
return self.mergeable_ranks
def convert_tokens_to_ids(self, tokens):
ids = []
# Remove support for py2
if isinstance(tokens, str):
if tokens in self.special_tokens:
return self.special_tokens[tokens]
else:
return self.encoder.get(tokens)
for token in tokens:
if token in self.special_tokens:
ids.append(self.special_tokens[token])
else:
ids.append(self.encoder.get(token))
if len(ids) > self.max_len:
logger.warning(
"Token indices sequence length is longer than the specified maximum "
" sequence length for this OpenAI GPT model ({} > {}). Running this"
" sequence through the model will result in indexing errors".format(
len(ids), self.max_len
)
)
return ids
def save_vocabulary(self, save_directory: str) -> Tuple[str]:
"""
Save only the vocabulary of the tokenizer (vocabulary + added tokens).
Returns:
`Tuple(str)`: Paths to the files saved.
"""
file_path = os.path.join(save_directory, "qwen.tiktoken")
with open(file_path, "w", encoding="utf8") as w:
for k, v in self.mergeable_ranks.items():
line = base64.b64encode(k).decode("utf8") + " " + str(v) + "\n"
w.write(line)
return (file_path,)
def tokenize(self, text: str, **kwargs) -> List[str]:
"""
Converts a string in a sequence of tokens, replacing unknown tokens with the `unk_token`.
Args:
text (`str`):
The sequence to be encoded.
pair (`str`, *optional*):
A second sequence to be encoded with the first.
add_special_tokens (`bool`, *optional*, defaults to `False`):
Whether or not to add the special tokens associated with the corresponding model.
kwargs (additional keyword arguments, *optional*):
Will be passed to the underlying model specific encode method. See details in
[`~PreTrainedTokenizerBase.__call__`]
Returns:
`List[str]`: The list of tokens.
"""
tokens = []
text = unicodedata.normalize("NFC", text)
for t in self.tokenizer.encode_ordinary(text):
tokens.append(self.decoder[t])
return tokens
def convert_tokens_to_string(self, tokens: List[str]) -> str:
"""
Converts a sequence of tokens in a single string. The most simple way to do it is `" ".join(tokens)` but we
often want to remove sub-word tokenization artifacts at the same time.
"""
text = "".join(tokens)
text = bytearray([self.byte_decoder[c] for c in text]).decode(
"utf-8", errors=self.errors
)
return text
@property
def vocab_size(self):
return self.tokenizer.n_vocab
def _convert_id_to_token(self, index: int) -> str:
raise NotImplementedError
def _tokenize(self, text, **kwargs):
"""
Converts a string in a sequence of tokens (string), using the tokenizer. Split in words for word-based
vocabulary or sub-words for sub-word-based vocabularies (BPE/SentencePieces/WordPieces).
Do NOT take care of added tokens.
"""
raise NotImplementedError
def _decode(
self,
token_ids: Union[int, List[int]],
skip_special_tokens: bool = False,
clean_up_tokenization_spaces: bool = None,
**kwargs,
) -> str:
if isinstance(token_ids, int):
token_ids = [token_ids]
return self.tokenizer.decode(token_ids)
|