423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-17 04:10:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

rename files

Browse Source
This commit is contained in:
hiyouga
2024-06-07 00:09:06 +08:00
parent 45d8be8f93
commit 74f96efef9
43 changed files with 53 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files

0
src/llamafactory/train/ppo/utils.py → src/llamafactory/train/ppo/ppo_utils.py
View File

4
src/llamafactory/train/ppo/trainer.py
View File

@@ -19,8 +19,8 @@ from trl.models.utils import unwrap_model_for_generation
from ...extras.callbacks import FixValueHeadModelCallback, LogCallback
from ...extras.logging import get_logger
from ...extras.misc import AverageMeter, count_parameters, get_current_device, get_logits_processor
from ..utils import create_custom_optimzer, create_custom_scheduler
from .utils import dump_layernorm, get_rewards_from_server, replace_model, restore_layernorm
from ..trainer_utils import create_custom_optimzer, create_custom_scheduler
from .ppo_utils import dump_layernorm, get_rewards_from_server, replace_model, restore_layernorm
if TYPE_CHECKING:

2
src/llamafactory/train/ppo/workflow.py
View File

@@ -9,7 +9,7 @@ from ...extras.callbacks import FixValueHeadModelCallback
from ...extras.misc import fix_valuehead_checkpoint
from ...extras.ploting import plot_loss
from ...model import load_model, load_tokenizer
from ..utils import create_ref_model, create_reward_model
from ..trainer_utils import create_ref_model, create_reward_model
from .trainer import CustomPPOTrainer