feat: add record-mode to Store for DPO/GRPO
- Store gains fetch_record/num_records alongside stream fetch/__len__ - save_bin/load_bin support per-record offsets via record_keys param - H5Store/MmapStore/JsonlStore all support dual stream+record access - DPODataset/GRPODataset use fetch_record, no cross-record concat - dpo_collate_fn + collate_fn wired through TrainConfig - fixes attention context leakage in DPO from windowed concatenation
This commit is contained in:
@@ -19,6 +19,7 @@ from astrai.serialization.checkpoint import (
|
||||
)
|
||||
from astrai.serialization.dataset import (
|
||||
load_bin,
|
||||
load_bin_offsets,
|
||||
load_h5,
|
||||
save_bin,
|
||||
save_h5,
|
||||
@@ -37,6 +38,7 @@ __all__ = [
|
||||
"save_safetensors",
|
||||
"save_torch",
|
||||
"load_bin",
|
||||
"load_bin_offsets",
|
||||
"load_h5",
|
||||
"save_bin",
|
||||
"save_h5",
|
||||
|
||||
Reference in New Issue
Block a user