refactor(pretrain): 更新预训练数据集输出目录名称
This commit is contained in:
@@ -5,5 +5,5 @@ if __name__ == "__main__":
|
||||
dataset = load_dataset("shjwudp/chinese-c4")
|
||||
process_dataset(
|
||||
dataset_dict=dataset,
|
||||
output_subdir="chinese-c4"
|
||||
output_subdir="chinese-c4-pretrain"
|
||||
)
|
||||
@@ -12,7 +12,7 @@ if __name__ == "__main__":
|
||||
|
||||
process_dataset(
|
||||
dataset_dict=dataset,
|
||||
output_subdir="chinese-wiki",
|
||||
output_subdir="chinese-wiki-pretrain",
|
||||
max_chunk_num=max_chunk_num,
|
||||
chunk_size=chunk_size,
|
||||
)
|
||||
@@ -5,5 +5,5 @@ if __name__ == "__main__":
|
||||
dataset = load_dataset("HuggingFaceFW/fineweb", "sample-10BT")
|
||||
process_dataset(
|
||||
dataset_dict=dataset,
|
||||
output_subdir="english-fineweb",
|
||||
output_subdir="english-fineweb-pretrain",
|
||||
)
|
||||
@@ -5,6 +5,6 @@ if __name__ == "__main__":
|
||||
dataset = load_dataset("Blaze7451/enwiki_structured_content")
|
||||
process_dataset(
|
||||
dataset_dict=dataset,
|
||||
output_subdir="english-wiki",
|
||||
output_subdir="english-wiki-pretrain",
|
||||
max_chunk_size=5,
|
||||
)
|
||||
Reference in New Issue
Block a user