YeAnbang d20c8ffd97 Add GRPO and Support RLVR for PPO (#6186) ... * add grpo, support rlvr * add grpo, support rlvr * tested deepseek r1 pipeline * add ci * verify grpo r1 * verify grpo r1 * update readme, remove unused code * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * remove path * clean code * fix circular import * fix ci OOM * fix ci OOM * skip kto tp, fix qwen generation --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>		2025-02-18 09:43:36 +08:00
..
hostfile	add SimPO	2024-06-24 02:12:20 +00:00
lora_config.json	[Chat] Fix lora (#5946)	2024-07-31 14:10:17 +08:00
train_dpo.py	[Coati] Train DPO using PP (#6054)	2024-10-11 19:32:00 +08:00
train_dpo.sh	refactor evaluation	2024-07-22 05:57:39 +00:00
train_grpo.py	Add GRPO and Support RLVR for PPO (#6186)	2025-02-18 09:43:36 +08:00
train_grpo.sh	Add GRPO and Support RLVR for PPO (#6186)	2025-02-18 09:43:36 +08:00
train_kto.py	[ColossalChat] Add PP support (#6001)	2024-08-21 10:47:39 +08:00
train_kto.sh	refactor evaluation	2024-07-22 05:57:39 +00:00
train_orpo.py	[ColossalChat] Add PP support (#6001)	2024-08-21 10:47:39 +08:00
train_orpo.sh	refactor evaluation	2024-07-22 05:57:39 +00:00
train_ppo.py	Add GRPO and Support RLVR for PPO (#6186)	2025-02-18 09:43:36 +08:00
train_ppo.sh	[ColossalChat] Hotfix for ColossalChat (#5910)	2024-07-19 13:40:07 +08:00
train_rm.py	[ColossalChat] Add PP support (#6001)	2024-08-21 10:47:39 +08:00
train_rm.sh	refactor evaluation	2024-07-22 05:57:39 +00:00
train_sft.py	[Coati] Train DPO using PP (#6054)	2024-10-11 19:32:00 +08:00
train_sft.sh	[Chat] Fix lora (#5946)	2024-07-31 14:10:17 +08:00