Update

app.py

@@ -200,6 +200,8 @@ with gr.Blocks(title="ChatGLM2-6B-int4", theme=gr.themes.Soft(text_size="sm")) a
         _ = """
             ## ChatGLM2-6B-int4
 
+            Try to refresh the browser and try again when  occasionally an error occurs.
+
             With a GPU, a query takes from a few seconds to a few tens of seconds, dependent on the number of words/characters
             the question and responses contain. The quality of the responses varies quite a bit it seems. Even the same
             question with the same parameters, asked at different times, can result in quite different responses.