Update app.py

app.py

@@ -11,7 +11,7 @@ import subprocess
 from huggingface_hub import hf_hub_download
 
 # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
-model = AutoModelForCausalLM.from_pretrained("TheBloke/manticore-13b-chat-pyg-GGUF", model_file="manticore-13b-chat-pyg.Q2_K.gguf", model_type="llama", gpu_layers=0)
+model = AutoModelForCausalLM.from_pretrained("TheBloke/manticore-13b-chat-pyg-GGUF", model_file="manticore-13b-chat-pyg.Q4_K_M.gguf", model_type="llama", gpu_layers=0)
 ins = '''[INST] <<FRIDAY>>
 Remember that your English name is "Shi-Ci" and your name in Chinese is "兮辞". You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
 If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.