add iterable argument to preprocess-cli

This commit is contained in:
Wing Lian
2025-01-27 14:31:12 -05:00
parent 887513285d
commit 1cfb8feb2d

View File

@@ -13,6 +13,12 @@ class PreprocessCliArgs:
debug_num_examples: int = field(default=1)
prompter: Optional[str] = field(default=None)
download: Optional[bool] = field(default=True)
iterable: Optional[bool] = field(
default=None,
metadata={
"help": "Use IterableDataset for streaming processing of large datasets"
},
)
@dataclass