refactor: 修改项目结构

This commit is contained in:
2026-03-21 21:25:59 +08:00
parent 5b47ab1dea
commit 909f1b400c
32 changed files with 535 additions and 703 deletions
+18
View File
@@ -0,0 +1,18 @@
from .tokenizer import BpeTokenizer
from .text import TextNormalizer
from .packing import SequencePacker
from .io import IOHandler
from .processors import ProcessorFactory, BaseProcessor
from .export import export_dataset
from .cache import cache_jsonl
__all__ = [
'BpeTokenizer',
'TextNormalizer',
'SequencePacker',
'IOHandler',
'ProcessorFactory',
'BaseProcessor',
'export_dataset',
'cache_jsonl',
]