10 lines
299 B
Python
10 lines
299 B
Python
from datasets import load_dataset
|
|
from modules.utils import process_dataset
|
|
|
|
if __name__ == "__main__":
|
|
dataset = load_dataset("Blaze7451/enwiki_structured_content")
|
|
process_dataset(
|
|
dataset_dict=dataset,
|
|
output_subdir="english-wiki-pretrain",
|
|
max_chunk_size=5,
|
|
) |