refactor: split mask builder by single/multi output

- Extract SingleOutputMaskBuilder for SFT and pretrain configs
- Extract MultiOutputMaskBuilder for DPO and GRPO configs
- Keep SectionedMaskBuilder as backward-compatible facade
- Register "single" and "multi" names in MaskBuilderFactory
- Add parity and rejection tests for concrete builders
This commit is contained in:
2026-07-08 21:18:34 +08:00
parent c8567a6f65
commit 841a582b28
4 changed files with 130 additions and 39 deletions
+4
View File
@@ -1,7 +1,9 @@
from astrai.preprocessing.builder import (
BaseMaskBuilder,
MaskBuilderFactory,
MultiOutputMaskBuilder,
SectionedMaskBuilder,
SingleOutputMaskBuilder,
)
from astrai.preprocessing.packing import (
PackingStrategy,
@@ -20,12 +22,14 @@ from astrai.preprocessing.writer import (
__all__ = [
"BaseMaskBuilder",
"MaskBuilderFactory",
"MultiOutputMaskBuilder",
"PackingStrategy",
"PackingStrategyFactory",
"Pipeline",
"PositionIdStrategy",
"PositionIdStrategyFactory",
"SectionedMaskBuilder",
"SingleOutputMaskBuilder",
"StoreWriter",
"StoreWriterFactory",
"filter_by_length",