重构代码

Author: Your Name

swift/plugin/tool_call.py

@@ -1,9 +1,10 @@
-from typing import Tuple,Any, Optional
+from typing import Tuple, Any, Optional
+
+
 class TOOL_CALL:
+
     def __call__(self, completion: str) -> Tuple[Any, bool, Optional[float]]:
         raise NotImplementedError
 
 
-tools = {
-    
-}
+tools = {}

swift/trainers/arguments.py

@@ -104,9 +104,9 @@ class GRPOArgumentsMixin:
     offload_optimizer: bool = False
     offload_model: bool = False
     gc_collect_after_offload: bool = False
-    is_reward_tool_call:bool = True #是否额外单独计算每个tool call的format得分
-    tool_call_weight:float = 1.0
-    tool_call:str = None
+    is_reward_tool_call: bool = True  #是否额外单独计算每个tool call的format得分
+    tool_call_weight: float = 1.0
+    tool_call: str = None
 
 
 @dataclass

swift/trainers/rlhf_arguments.py

@@ -1,5 +1,5 @@
 from dataclasses import dataclass, field
-from typing import List, Optional,Callable
+from typing import List, Optional, Callable
 
 from trl import CPOConfig as HfCPOConfig
 from trl import DPOConfig as HfDPOConfig