wehub-resource-sync
47 lines
1.8 KiB
Python
47 lines
1.8 KiB
Python
# Copyright (c) ModelScope Contributors. All rights reserved.
|
|
from typing import TYPE_CHECKING
|
|
|
|
from swift.utils.import_utils import _LazyModule
|
|
|
|
if TYPE_CHECKING:
|
|
from .args_mixin import GRPOArgumentsMixin, VllmArguments
|
|
from .arguments import CPOConfig, DPOConfig, GKDConfig, GRPOConfig, KTOConfig, ORPOConfig, PPOConfig, RewardConfig
|
|
from .cpo_trainer import CPOTrainer
|
|
from .dpo_trainer import DPOTrainer
|
|
from .gkd_trainer import GKDTrainer
|
|
from .grpo_trainer import GRPOTrainer
|
|
from .kto_trainer import KTOTrainer
|
|
from .orpo_trainer import ORPOTrainer
|
|
from .ppo_trainer import PPOTrainer
|
|
from .reward_trainer import RewardTrainer
|
|
from .rlhf_mixin import RLHFTrainerMixin
|
|
from .utils import _ForwardRedirection, patch_lora_merge, patch_lora_unmerge, round_robin
|
|
from .vllm_client import VLLMClient, VLLMInferClient
|
|
else:
|
|
_import_structure = {
|
|
'cpo_trainer': ['CPOTrainer'],
|
|
'dpo_trainer': ['DPOTrainer'],
|
|
'grpo_trainer': ['GRPOTrainer'],
|
|
'kto_trainer': ['KTOTrainer'],
|
|
'orpo_trainer': ['ORPOTrainer'],
|
|
'ppo_trainer': ['PPOTrainer'],
|
|
'reward_trainer': ['RewardTrainer'],
|
|
'gkd_trainer': ['GKDTrainer'],
|
|
'rlhf_mixin': ['RLHFTrainerMixin'],
|
|
'args_mixin': ['VllmArguments', 'GRPOArgumentsMixin'],
|
|
'utils': ['patch_lora_merge', 'patch_lora_unmerge', 'round_robin', '_ForwardRedirection'],
|
|
'vllm_client': ['VLLMClient', 'VLLMInferClient'],
|
|
'arguments':
|
|
['DPOConfig', 'CPOConfig', 'KTOConfig', 'ORPOConfig', 'PPOConfig', 'RewardConfig', 'GRPOConfig', 'GKDConfig']
|
|
}
|
|
|
|
import sys
|
|
|
|
sys.modules[__name__] = _LazyModule(
|
|
__name__,
|
|
globals()['__file__'],
|
|
_import_structure,
|
|
module_spec=__spec__,
|
|
extra_objects={},
|
|
)
|