Commit Graph

2 Commits

Author SHA1 Message Date
hanluzhi0429@gmail.com 4a3c349d33 [2025.06.22] add reward model、PPO、GRPO train code 2025-06-22 22:57:51 +08:00
hanluzhi0429@gmail.com aa0267da53 [2025.06.19] pre_token corpus and add cold start 2025-06-19 18:23:19 +08:00