Update app.py

app.py

@@ -67,7 +67,7 @@ generation_config = AutoConfig.from_pretrained(
 # send additional parameters to model for generation
 
 #model = llama_cpp.Llama(model_path = tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf AutoModelForCausalLM.from_pretrained(llm_model, model_file = "tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf", model_type="llama", gpu_layers=0, config = generation_config)
-model = LlamaCpp(
+model = Llama(
     model_path="./tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf",
     chat_format="llama-2",
     n_gpu_layers = 0,