File size: 9,618 Bytes
7b54955
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# 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."""

import base64
import logging
import os
import unicodedata
from typing import Collection, Dict, List, Set, Tuple, Union

import tiktoken
from transformers import PreTrainedTokenizer, AddedToken

logger = logging.getLogger(__name__)


VOCAB_FILES_NAMES = {"vocab_file": "qwen.tiktoken"}

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+"""
ENDOFTEXT = "<|endoftext|>"
IMSTART = "<|im_start|>"
IMEND = "<|im_end|>"
# as the default behavior is changed to allow special tokens in
# regular texts, the surface forms of special tokens need to be
# as different as possible to minimize the impact
EXTRAS = tuple((f"<|extra_{i}|>" for i in range(205)))
# changed to use actual index to avoid misconfiguration with vocabulary expansion
SPECIAL_START_ID = 151643
SPECIAL_TOKENS = tuple(
    enumerate(
        (
            (
                ENDOFTEXT,
                IMSTART,
                IMEND,
            )
            + EXTRAS
        ),
        start=SPECIAL_START_ID,
    )
)
SPECIAL_TOKENS_SET = set(t for i, t in SPECIAL_TOKENS)


def _load_tiktoken_bpe(tiktoken_bpe_file: str) -> Dict[bytes, int]:
    with open(tiktoken_bpe_file, "rb") as f:
        contents = f.read()
    return {
        base64.b64decode(token): int(rank)
        for token, rank in (line.split() for line in contents.splitlines() if line)
    }


class QWenTokenizer(PreTrainedTokenizer):
    """QWen tokenizer."""

    vocab_files_names = VOCAB_FILES_NAMES

    def __init__(
        self,
        vocab_file,
        errors="replace",
        extra_vocab_file=None,
        **kwargs,
    ):
        super().__init__(**kwargs)

        # how to handle errors in decoding UTF-8 byte sequences
        # use ignore if you are in streaming inference
        self.errors = errors  

        self.mergeable_ranks = _load_tiktoken_bpe(vocab_file)  # type: Dict[bytes, int]
        self.special_tokens = {
            token: index
            for index, token in SPECIAL_TOKENS
        }

        # try load extra vocab from file
        if extra_vocab_file is not None:
            used_ids = set(self.mergeable_ranks.values()) | set(self.special_tokens.values())
            extra_mergeable_ranks = _load_tiktoken_bpe(extra_vocab_file)
            for token, index in extra_mergeable_ranks.items():
                if token in self.mergeable_ranks:
                    logger.info(f"extra token {token} exists, skipping")
                    continue
                if index in used_ids:
                    logger.info(f'the index {index} for extra token {token} exists, skipping')
                    continue
                self.mergeable_ranks[token] = index
            # the index may be sparse after this, but don't worry tiktoken.Encoding will handle this

        enc = tiktoken.Encoding(
            "Qwen",
            pat_str=PAT_STR,
            mergeable_ranks=self.mergeable_ranks,
            special_tokens=self.special_tokens,
        )
        assert (
            len(self.mergeable_ranks) + len(self.special_tokens) == enc.n_vocab
        ), f"{len(self.mergeable_ranks) + len(self.special_tokens)} != {enc.n_vocab} in encoding"

        self.decoder = {
            v: k for k, v in self.mergeable_ranks.items()
        }  # type: dict[int, bytes|str]
        self.decoder.update({v: k for k, v in self.special_tokens.items()})

        self.tokenizer = enc  # type: tiktoken.Encoding

        self.eod_id = self.tokenizer.eot_token
        self.im_start_id = self.special_tokens[IMSTART]
        self.im_end_id = self.special_tokens[IMEND]

    def __getstate__(self):
        # for pickle lovers
        state = self.__dict__.copy()
        del state["tokenizer"]
        return state

    def __setstate__(self, state):
        # tokenizer is not python native; don't pass it; rebuild it
        self.__dict__.update(state)
        enc = tiktoken.Encoding(
            "Qwen",
            pat_str=PAT_STR,
            mergeable_ranks=self.mergeable_ranks,
            special_tokens=self.special_tokens,
        )
        self.tokenizer = enc

    def __len__(self) -> int:
        return self.tokenizer.n_vocab

    def get_vocab(self) -> Dict[bytes, int]:
        return self.mergeable_ranks

    def convert_tokens_to_ids(
        self, tokens: Union[bytes, str, List[Union[bytes, str]]]
    ) -> List[int]:
        ids = []
        if isinstance(tokens, (str, bytes)):
            if tokens in self.special_tokens:
                return self.special_tokens[tokens]
            else:
                return self.mergeable_ranks.get(tokens)
        for token in tokens:
            if token in self.special_tokens:
                ids.append(self.special_tokens[token])
            else:
                ids.append(self.mergeable_ranks.get(token))
        return ids

    def _add_tokens(
        self,
        new_tokens: Union[List[str], List[AddedToken]],
        special_tokens: bool = False,
    ) -> int:
        if not special_tokens and new_tokens:
            raise ValueError("Adding regular tokens is not supported")
        for token in new_tokens:
            surface_form = token.content if isinstance(token, AddedToken) else token
            if surface_form not in SPECIAL_TOKENS_SET:
                raise ValueError("Adding unknown special tokens is not supported")
        return 0

    def save_vocabulary(self, save_directory: str, **kwargs) -> Tuple[str]:
        """
        Save only the vocabulary of the tokenizer (vocabulary).

        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,
        allowed_special: Union[Set, str] = "all",
        disallowed_special: Union[Collection, str] = (),
        **kwargs,
    ) -> List[Union[bytes, str]]:
        """
        Converts a string in a sequence of tokens.

        Args:
            text (`str`):
                The sequence to be encoded.
            allowed_special (`Literal["all"]` or `set`):
                The surface forms of the tokens to be encoded as special tokens in regular texts.
                Default to "all".
            disallowed_special (`Literal["all"]` or `Collection`):
                The surface forms of the tokens that should not be in regular texts and trigger errors.
                Default to an empty tuple.

            kwargs (additional keyword arguments, *optional*):
                Will be passed to the underlying model specific encode method.

        Returns:
            `List[bytes|str]`: The list of tokens.
        """
        tokens = []
        text = unicodedata.normalize("NFC", text)

        # this implementation takes a detour: text -> token id -> token surface forms
        for t in self.tokenizer.encode(
            text, allowed_special=allowed_special, disallowed_special=disallowed_special
        ):
            tokens.append(self.decoder[t])
        return tokens

    def convert_tokens_to_string(self, tokens: List[Union[bytes, str]]) -> str:
        """
        Converts a sequence of tokens in a single string.
        """
        text = ""
        temp = b""
        for t in tokens:
            if isinstance(t, str):
                if temp:
                    text += temp.decode("utf-8", errors=self.errors)
                    temp = b""
                text += t
            elif isinstance(t, bytes):
                temp += t
            else:
                raise TypeError("token should only be of type types or str")
        if temp:
            text += temp.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) -> Union[bytes, str]:
        """Converts an id to a token, special tokens included"""
        if index in self.decoder:
            return self.decoder[index]
        raise ValueError("unknown ids")

    def _convert_token_to_id(self, token: Union[bytes, str]) -> int:
        """Converts a token to an id using the vocab, special tokens included"""
        if token in self.special_tokens:
            return self.special_tokens[token]
        if token in self.mergeable_ranks:
            return self.mergeable_ranks[token]
        raise ValueError("unknown token")

    def _tokenize(self, text: str, **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,
        errors: str = None,
        **kwargs,
    ) -> str:
        if isinstance(token_ids, int):
            token_ids = [token_ids]
        if skip_special_tokens:
            token_ids = [i for i in token_ids if i < self.eod_id]
        return self.tokenizer.decode(token_ids, errors=errors or self.errors)