Update app.py

app.py

@@ -76,7 +76,7 @@ callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
 def create_conversational_chain(database):
     llama_llm = LlamaCpp(
         # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llama-2-7b-chat.Q8_0.gguf
-        llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7b-Chat-GGUF", model_file="llama-2-7b-chat.Q8_0.gguf", model_type="llama", gpu_layers=0),
+        model_path = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7b-Chat-GGUF", model_file="llama-2-7b-chat.Q8_0.gguf", model_type="llama", gpu_layers=0),
         temperature=0.75,
         max_tokens=200,
         top_p=1,