Update app.py

app.py

@@ -17,10 +17,10 @@ def load_llm():
     )
     llm = Llama(
         model_path=model_path,
-        n_ctx=512
+        n_ctx=512,
         n_threads=max(2, os.cpu_count() or 2),
         n_gpu_layers=0,
-        n_batch=32
+        n_batch=32,
         verbose=False,
     )
     return llm