Update app.py

app.py

@@ -17,7 +17,7 @@ llm = Llama(
     model_path=base_model_path,
     lora_path=adapter_path,
     n_ctx=1024,       # Context length, set manually since adapter lacks it
-    n_threads=2,     # Adjust based on your system
+    n_threads=4,     # Adjust based on your system
     n_gpu_layers=0    # Set to >0 if GPU acceleration is desired and supported
 )
 
@@ -61,4 +61,4 @@ iface = gr.Interface(
 )
 
 # Launch the app
-iface.launch()
+iface.launch(debug=True)