Update app.py

app.py

@@ -88,7 +88,7 @@ def respond(
             model_id = "ggml-model-Q6_K.gguf"
             llama = Llama(f"models/{model_id}",flash_attn=False,
                         n_gpu_layers=0,
-                        n_ctx=max_tokens
+                        n_ctx=max_tokens,
                         n_threads=2,
                         n_threads_batch=2)