diff --git a/llama_cpp/server/app.py b/llama_cpp/server/app.py index 2d20f37..e1045af 100644 --- a/llama_cpp/server/app.py +++ b/llama_cpp/server/app.py @@ -169,6 +169,7 @@ class CreateChatCompletionRequest(BaseModel): model: str = model_field # llama.cpp specific parameters + top_k: int = 40, repeat_penalty: float = 1.1 class Config: