AstrAI

Commit Graph

Author	SHA1	Message	Date
ViperEkura	841a582b28	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	2026-07-08 21:18:34 +08:00
ViperEkura	25d4ea3f91	refactor : 压缩测试代码，消除重复 - fixture 替代重复实例化和 tokenizer 落盘 - parametrize 合并同构测试 - helper 消除 save_h5 + DatasetFactory.load 样板 - 净减 272 行	2026-06-19 14:54:39 +08:00
ViperEkura	02a7cb9fa0	feat : preprocessing 支持 DPO/GRPO 多输出格式 - InputConfig 新增 sources 字段驱动多输出映射 - SectionedMaskBuilder 提取 _process_sections/_build_multi 模板方法 - Pipeline 泛化 accumulate 逻辑处理多 key 结果 - 测试拆分为 config/builder/pipeline 三文件，纯函数风格	2026-06-03 10:32:10 +08:00

Author

SHA1

Message

Date

ViperEkura

841a582b28

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

2026-07-08 21:18:34 +08:00

ViperEkura

25d4ea3f91

refactor : 压缩测试代码，消除重复

- fixture 替代重复实例化和 tokenizer 落盘
- parametrize 合并同构测试
- helper 消除 save_h5 + DatasetFactory.load 样板
- 净减 272 行

2026-06-19 14:54:39 +08:00

ViperEkura

02a7cb9fa0

feat : preprocessing 支持 DPO/GRPO 多输出格式

- InputConfig 新增 sources 字段驱动多输出映射
- SectionedMaskBuilder 提取 _process_sections/_build_multi 模板方法
- Pipeline 泛化 accumulate 逻辑处理多 key 结果
- 测试拆分为 config/builder/pipeline 三文件，纯函数风格

2026-06-03 10:32:10 +08:00

3 Commits