File size: 2,032 Bytes
0558aa4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright (c) 2025, NVIDIA CORPORATION.  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.

from megatron.core.datasets.megatron_tokenizer import MegatronLegacyTokenizer as MegatronTokenizer


class NullTokenizer(MegatronTokenizer):
    """
    Synthetic tokenizer for performance benchmarking and debugging

    Args:
        vocab_size: vocabulary size for embedding
    """

    def __init__(self, vocab_size):
        super().__init__(None, vocab_size=vocab_size)
        self._vocab_size_without_eod = int(vocab_size)
        self._eod_id = self._vocab_size_without_eod

    def tokenize(self, text):
        return [int(x) for x in text.split(' ')]

    def detokenize(self, ids):
        text = [str(x) for x in ids]
        return ' '.join(text)

    def offsets(self, ids: list[int], text: str) -> list[int]:
        offsets, start_idx = [], 0
        for id_ in ids:
            offsets.append(start_idx)
            start_idx += 1 + len(str(id_))
        return offsets

    @property
    def vocab_size(self):
        return self._vocab_size_without_eod + 1

    @property
    def vocab(self):
        raise NotImplementedError

    @property
    def inv_vocab(self):
        raise NotImplementedError

    @property
    def cls(self):
        return -1

    @property
    def sep(self):
        return -1

    @property
    def mask(self):
        return -1

    @property
    def eod(self):
        return self._eod_id

    @property
    def additional_special_tokens_ids(self):
        return None