Update app.py

app.py

@@ -12,6 +12,7 @@ os.system("ulimit -l unlimited")
 app = FastAPI()
 
 hf_hub_download("TheBloke/deepseek-coder-1.3b-base-GGUF", "deepseek-coder-1.3b-base.Q5_K_M.gguf", local_dir="./")
+'''
 model_l = Llama(model_path="./deepseek-coder-1.3b-base.Q5_K_M.gguf", n_ctx=16192, n_gpu_layers=0, n_threads=2, use_mlock=True)
 
 
@@ -38,7 +39,7 @@ async def completion(request: Request):
     except:
         return {"responses": "Error!"}
 
-
+'''
 app = create_app(
         Settings(
             n_threads=2,  # set to number of cpu cores