ViperEkura a1ea26d367 fix: rewrite GRPO data pipeline for offline record-level access ... - process_list_field returns List[List[int]] preserving per-response boundaries - GRPODataset rewritten to record-level __getitem__ (no windowing/stride) - grpo_collate_fn pads variable-length responses into [B, G, R] tensors - JsonlStore detects nested List[List[int]] and stores List[Tensor] per record - Store._normalize skips nested-list keys from cumsum bookkeeping - Pipeline._flush handles nested lists without cross-record flattening - Export grpo_collate_fn from astrai.dataset - 6 new GRPO tests + 2 updated builder tests, 114 total pass		2026-07-17 14:34:41 +08:00
..
__init__.py	refactor: split mask builder by single/multi output	2026-07-08 21:18:34 +08:00
builder.py	fix: rewrite GRPO data pipeline for offline record-level access	2026-07-17 14:34:41 +08:00
packing.py	feat: implement bfd_split packing strategy	2026-07-17 12:38:56 +08:00
pipeline.py	fix: rewrite GRPO data pipeline for offline record-level access	2026-07-17 14:34:41 +08:00
position_id.py	fix : 修复策略相关文件的类型注解与抽象方法体	2026-06-14 16:20:10 +08:00
writer.py	feat: add JSONL dataset store with on-the-fly tokenization	2026-07-04 15:42:33 +08:00