refactor(to_ids): 注释掉中文维基百科数据集的处理

This commit is contained in:
2025-07-15 07:01:26 +08:00
parent 95a3568328
commit 1c7e49a631
+1 -1
View File
@@ -11,7 +11,7 @@ if __name__ == "__main__":
# os.path.join("dataset", "chinese-c4"),
# os.path.join("dataset", "english-fineweb"),
# os.path.join("dataset", "english-wiki"),
os.path.join("dataset", "chinese-wiki"),
# os.path.join("dataset", "chinese-wiki"),
]
base_out_dir = "pkl_output"
files = []