Update app.py

app.py

@@ -90,7 +90,7 @@ def respond(
                         n_gpu_layers=0,
                         n_ctx=max_tokens,
                         n_threads=2,
-                        n_threads_batch=2)
+                        n_threads_batch=2,verbose=False)
        
         tokens = llama.tokenize(f"{message}".encode("utf-8"))
         llama.encode(tokens)