2 Commits (cfa8247f20b65fd193bd7fb589f2b061bc39f4a7)

Author	SHA1	Message	Date
root	d37bfa9d75	[update] harden training and inference reliability ... Fix truncated SFT/DPO label masking and resume-safe gradient accumulation to prevent unstable optimization, and add explicit eval backend selection plus regression checks for safer local validation.	2026-04-05 18:11:37 +00:00
jingyaogong	101d7df2da	[update] minimind-3	2026-03-25 23:57:45 +08:00