chore: 将data 模块命名为dataset

astrai/__init__.py

@@ -6,7 +6,7 @@ from astrai.config import (
     TrainConfig,
 )
 from astrai.factory import BaseFactory
-from astrai.data import DatasetFactory
+from astrai.dataset import DatasetFactory
 from astrai.tokenizer import BpeTokenizer
 from astrai.inference.generator import (
     BatchGenerator,

astrai/dataset/__init__.py

@@ -1,10 +1,10 @@
-from astrai.data.dataset import (
+from astrai.dataset.dataset import (
     BaseDataset,
     DatasetFactory,
     BaseSegmentFetcher,
     MultiSegmentFetcher,
 )
-from astrai.data.sampler import ResumableDistributedSampler
+from astrai.dataset.sampler import ResumableDistributedSampler
 
 __all__ = [
     # Base classes

astrai/trainer/train_context.py

@@ -7,7 +7,7 @@ from torch.optim.lr_scheduler import LRScheduler
 from torch.utils.data import DataLoader
 
 from astrai.config.train_config import TrainConfig
-from astrai.data import ResumableDistributedSampler
+from astrai.dataset import ResumableDistributedSampler
 from astrai.serialization import Checkpoint
 from astrai.parallel.setup import get_current_device, get_rank, get_world_size
 from astrai.trainer.strategy import BaseStrategy, StrategyFactory