Update app.py

app.py

@@ -3,7 +3,7 @@ import gradio as gr
 from ctransformers import AutoModelForCausalLM
 
 # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
-llm = AutoModelForCausalLM.from_pretrained("TheBloke/WizardLM-7B-uncensored-GGUF", model_file="WizardLM-7B-uncensored.Q2_K.gguf", model_type="llama", stream=True)
+llm = AutoModelForCausalLM.from_pretrained("TheBloke/WizardLM-7B-uncensored-GGUF", model_file="WizardLM-7B-uncensored.Q3_K_M.gguf", model_type="llama", stream=True)
 history = ["Chatbot:"]
 
 def generate_response(message):