feat: 添加中文维基数据集处理脚本

2025-07-11 10:31:10 +08:00
parent a8f05cccd6
commit 9a417ab6a5
2 changed files with 31 additions and 0 deletions
@@ -7,3 +7,6 @@ pkl_output/*

 # tokenzier
 tokenizer.json
+
+# test unit
+test*