From a5aa6c1478de7cc16b654df533be3dee6519c42a Mon Sep 17 00:00:00 2001 From: Lucas Doyle Date: Sat, 29 Apr 2023 11:52:20 -0700 Subject: [PATCH] llama_cpp server: add missing top_k param to CreateChatCompletionRequest `llama.create_chat_completion` definitely has a `top_k` argument, but its missing from `CreateChatCompletionRequest`. decision: add it --- llama_cpp/server/app.py | 1 + 1 file changed, 1 insertion(+) 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: