Update app.py

app.py

@@ -27,8 +27,8 @@ def load_model():
         model_type = 'llama',
         max_new_tokens = 1096,
         temperature = 0.2,
-        repetition_penalty = 1.13
-        # gpu_layers = 2
+        repetition_penalty = 1.13,
+        gpu_layers = 2
     )
     return llm
 
@@ -61,4 +61,4 @@ with gr.Blocks(title="code llama 7b") as demo:
     
     msg.submit(respond,[msg, chatbot],[msg, chatbot])
 
-demo.launch(share=True)
+demo.launch()