support DPO training (2305.18290)

Former-commit-id: 6d98de148e4af63a7028dfaeb6cf86eb56a4488f
This commit is contained in:
hiyouga
2023-08-11 03:02:53 +08:00
parent 72dfd74005
commit ca719a8697
33 changed files with 513 additions and 192 deletions

View File

@@ -4,7 +4,7 @@ import threading
import time
import transformers
from transformers.trainer import TRAINING_ARGS_NAME
from typing import Generator, List, Optional, Tuple
from typing import Generator, List, Tuple
from llmtuner.extras.callbacks import LogCallback
from llmtuner.extras.constants import DEFAULT_MODULE