5 Commits (19db1a10edc61132ece6349bdac7aae5629226f8)

Author	SHA1	Message	Date
guomin	19db1a10ed	fix 5-dpo train	2025-01-31 23:21:43 +08:00
gongjy	02adb7bc0d	update trl	2024-10-13 22:44:28 +08:00
gongjy	135421690e	update data_process	2024-10-12 19:46:08 +08:00
gongjy	2698f6b57d	update data_process	2024-10-12 18:47:08 +08:00
gongjy	8be42693f6	MiniMind first open source	2024-08-28 16:41:44 +08:00