Update app.py

app.py

@@ -23,8 +23,10 @@ print(f"Model downloaded to: {model_path}")
 
 llm = Llama(
     model_path=model_path,
+    n_threads=2,
+    n_batch=256,
     n_gpu_layers=0,       # GPU acceleration if available
-    n_ctx=4096,
+    n_ctx=2048,
     chat_format="llama-3",
 )