fix stop param

data/dataset_info.json

@@ -459,4 +459,4 @@
     },
     "folder": "python"
   }
-}
+}

src/llmtuner/api/chat.py

@@ -103,7 +103,7 @@ async def create_chat_completion_response(
         top_p=request.top_p,
         max_new_tokens=request.max_tokens,
         num_return_sequences=request.n,
-        stop=request.stop
+        stop=request.stop,
     )
 
     prompt_length, response_length = 0, 0
@@ -145,6 +145,9 @@ async def create_stream_chat_completion_response(
     if tools:
         raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Cannot stream function calls.")
 
+    if request.n > 1:
+        raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Cannot stream multiple responses.")
+
     yield _create_stream_chat_completion_chunk(
         completion_id=completion_id, model=request.model, delta=ChatCompletionMessage(role=Role.ASSISTANT, content="")
     )
@@ -156,7 +159,7 @@ async def create_stream_chat_completion_response(
         temperature=request.temperature,
         top_p=request.top_p,
         max_new_tokens=request.max_tokens,
-        stop=request.stop
+        stop=request.stop,
     ):
         if len(new_token) != 0:
             yield _create_stream_chat_completion_chunk(

src/llmtuner/api/protocol.py

@@ -77,8 +77,8 @@ class ChatCompletionRequest(BaseModel):
     top_p: Optional[float] = None
     n: int = 1
     max_tokens: Optional[int] = None
+    stop: Optional[Union[str, List[str]]] = None
     stream: bool = False
-    stop: Union[Optional[str], List[str]] = None
 
 
 class ChatCompletionResponseChoice(BaseModel):

src/llmtuner/chat/hf_engine.py

@@ -73,6 +73,10 @@ class HuggingfaceEngine(BaseEngine):
         repetition_penalty = input_kwargs.pop("repetition_penalty", None)
         max_length = input_kwargs.pop("max_length", None)
         max_new_tokens = input_kwargs.pop("max_new_tokens", None)
+        stop = input_kwargs.pop("stop", None)
+
+        if stop is not None:
+            raise ValueError("Stop parameter is not supported in Huggingface engine yet.")
 
         generating_args.update(
             dict(