9 lines
225 B
Python
9 lines
225 B
Python
from utils import process_dataset
|
|
|
|
if __name__ == "__main__":
|
|
process_dataset(
|
|
dataset_name="wikimedia/wikipedia",
|
|
output_subdir="chinese-wiki",
|
|
dataset_config="zh",
|
|
max_chunk_size=5,
|
|
) |