Update app.py

app.py

@@ -181,8 +181,11 @@ with gr.Blocks(title="ChatGLM2-6B-int4", theme=gr.themes.Soft(text_size="sm")) a
 
     with gr.Accordion("Info", open=False):
         _ = """
-            A query takes from 30 seconds to a few tens of seconds, dependent on the number of words/characters 
-            the question and answer contain.
+            ## ChatGLM2-6B-int4
+            
+            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.
 
             * Low temperature: responses will be more deterministic and focused; High temperature: responses more creative.