Files
AstrAI/astrai/dataset/__init__.py
T
ViperEkura 115192c67c refactor: remove H5 storage backend in favor of mmap bin
- Remove H5Store, H5Writer, save_h5/load_h5 and h5py dependency
- MmapStore (bin) is the sole pre-tokenized storage backend
- Move setup_logging after imports to fix E402 in __init__.py
- Clean up unused imports across test files
- Move inline test imports to file top
2026-07-29 12:50:27 +08:00

38 lines
652 B
Python

from astrai.dataset.dataset import (
BaseDataset,
DatasetFactory,
dpo_collate_fn,
grpo_collate_fn,
)
from astrai.dataset.sampler import RDSampler
from astrai.dataset.storage import (
JsonlStore,
MmapStore,
Recordable,
Store,
StoreFactory,
Streamable,
detect_format,
)
from astrai.serialization import (
load_bin,
save_bin,
)
__all__ = [
"BaseDataset",
"DatasetFactory",
"dpo_collate_fn",
"grpo_collate_fn",
"Store",
"Streamable",
"Recordable",
"StoreFactory",
"MmapStore",
"JsonlStore",
"detect_format",
"save_bin",
"load_bin",
"RDSampler",
]