Update app.py

app.py

@@ -3,8 +3,8 @@ 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.
-model_path = "TheBloke/WizardLM-7B-uncensored.Q3_K_S.gguf"
-llm = AutoModelForCausalLM.from_pretrained(model_path, model_type="llama",stream=True)
+llm = AutoModelForCausalLM.from_pretrained("TheBloke/WizardLM-7B-uncensored-GGUF", model_file="WizardLM-7B-uncensored.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
+
 
 def generate_response(message):
     response = llm(message)