- ascend_extras
- cispo_trainer
- data_preprocess
- dppo_trainer
- gdpo_trainer
- generation
- gmpo_trainer
- gpg_trainer
- grpo_trainer
- gspo_trainer
- mtp_trainer
- on_policy_distillation_trainer
- otb_trainer
- ppo_trainer
- prefix_grouper
- profile
- reinforce_plus_plus_trainer
- remax_trainer
- rloo_trainer
- rollout_correction
- router_replay
- sapo_trainer
- sft
- tuning
- tutorial
- 8.18 kB