mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-08-01 07:46:55 +00:00
d20c8ffd97
* 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>
21 lines
431 B
Python
Executable File
21 lines
431 B
Python
Executable File
from .base import OLTrainer, SLTrainer
|
|
from .dpo import DPOTrainer
|
|
from .grpo import GRPOTrainer
|
|
from .kto import KTOTrainer
|
|
from .orpo import ORPOTrainer
|
|
from .ppo import PPOTrainer
|
|
from .rm import RewardModelTrainer
|
|
from .sft import SFTTrainer
|
|
|
|
__all__ = [
|
|
"SLTrainer",
|
|
"OLTrainer",
|
|
"RewardModelTrainer",
|
|
"SFTTrainer",
|
|
"PPOTrainer",
|
|
"DPOTrainer",
|
|
"ORPOTrainer",
|
|
"KTOTrainer",
|
|
"GRPOTrainer",
|
|
]
|