Update app.py

app.py

@@ -27,7 +27,7 @@ n_gpu_layers = 40 # Change this value based on your model and your GPU VRAM pool
 n_batch = 256 
 
 llm = LlamaCpp(
-    model_path, callbacks=[StreamingStdOutCallbackHandler()]
+    model_path=model_path, callbacks=[StreamingStdOutCallbackHandler()]
 )
 
 #llm = LLM = G4FLLM(model=models.gpt_35_turbo,provider=Provider.DeepAi,)