add utils for data process

This commit is contained in:
coffee
2025-04-29 18:28:45 +08:00
parent 57a4401c54
commit f6206ce421
+1
View File
@@ -11,3 +11,4 @@ def extract_completions(json_file_path, output_file_path):
output_file.write(completion + '\n') output_file.write(completion + '\n')
extract_completions('corpus/wikipedia-cn-20230720-filtered.json', 'corpus/wikipedia.txt') extract_completions('corpus/wikipedia-cn-20230720-filtered.json', 'corpus/wikipedia.txt')