Update app.py

app.py

@@ -105,8 +105,8 @@ def respond(
                 n_gpu_layers=0,
                 n_batch=8,
                 n_ctx=2048,
-                n_threads=2,
-                n_threads_batch=2,
+                n_threads=8,
+                n_threads_batch=8,
             )
             llm_model = model
         provider = LlamaCppPythonProvider(llm)
@@ -165,11 +165,7 @@ def respond(
 # Create a chat interface
 demo = gr.ChatInterface(
     respond,
-    examples=[
-        ["What is the capital of France?"],
-        ["Tell me something about artificial intelligence."],
-        ["What is gravity?"],
-    ],
+    examples=[["What is the capital of France?"], ["Tell me something about artificial intelligence."], ["What is gravity?"]],
     additional_inputs_accordion=gr.Accordion(
         label="⚙️ Parameters", open=False, render=False
     ),