mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-07-18 17:31:53 +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>
29 lines
792 B
Python
Executable File
29 lines
792 B
Python
Executable File
from .base import BaseModel
|
|
from .critic import Critic
|
|
from .generation import generate, generate_streaming, prepare_inputs_fn, update_model_kwargs_fn
|
|
from .lora import LoraConfig, convert_to_lora_module, lora_manager
|
|
from .loss import DpoLoss, KTOLoss, LogExpLoss, LogSigLoss, PolicyLoss, ValueLoss
|
|
from .reward_model import RewardModel
|
|
from .rlvr_reward_model import RLVRRewardModel
|
|
from .utils import disable_dropout
|
|
|
|
__all__ = [
|
|
"BaseModel",
|
|
"Critic",
|
|
"RewardModel",
|
|
"RLVRRewardModel",
|
|
"PolicyLoss",
|
|
"ValueLoss",
|
|
"LogSigLoss",
|
|
"LogExpLoss",
|
|
"LoraConfig",
|
|
"lora_manager",
|
|
"convert_to_lora_module",
|
|
"DpoLoss",
|
|
"KTOLoss" "generate",
|
|
"generate_streaming",
|
|
"disable_dropout",
|
|
"update_model_kwargs_fn",
|
|
"prepare_inputs_fn",
|
|
]
|