Update app.py

app.py

@@ -1,10 +1,11 @@
 import os
-import time
 import subprocess
-import requests
-import tarfile
 import sys
+import tarfile
+import time
+
 import gradio as gr
+import requests
 from huggingface_hub import hf_hub_download
 
 # Llama-cpp-python, f- you for not updating for months! :(
@@ -114,7 +115,7 @@ def predict(message, history, system_prompt, temperature):
 
 
 with gr.Blocks(theme="soft") as demo:
-    gr.Markdown("## Qwen3 Inference via llama-server")
+    gr.Markdown("Test if we can load load gguf models with llama.cpp's new server API.")
 
     chat_interface = gr.ChatInterface(
         fn=predict,