Update app.py

app.py

@@ -107,16 +107,14 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
     gr.HTML("""<h1 align="center">ChatGLM2-6B-int4</h1>""")
     with gr.Accordion("Info", open=False):
         _ = """
-            Takes from 30 seconds to a few hundred seconds, dependent on the number of words/characters 
+            A query takes from 30 seconds to a few hundred seconds, dependent on the number of words/characters 
             the question and answer contain.
 
-            Low temperature: responses will be more deterministic and focused; High temperature: more creative
-            
-            Suggested temperatures -- translation: up to 0.3; chatting: > 0.4
+            * Low temperature: responses will be more deterministic and focused; High temperature: more creative. Suggested temperatures -- translation: up to 0.3; chatting: > 0.4
 
-            Top P controls dynamic vocabulary selection based on context. 
+            * Top P controls dynamic vocabulary selection based on context. 
 
-            For a table of of example values for different scenarios, refer to https://community.openai.com/t/cheat-sheet-mastering-temperature-and-top-p-in-chatgpt-api-a-few-tips-and-tricks-on-controlling-the-creativity-deterministic-output-of-prompt-responses/172683
+            For a table of of example values for different scenarios, refer to [this](https://community.openai.com/t/cheat-sheet-mastering-temperature-and-top-p-in-chatgpt-api-a-few-tips-and-tricks-on-controlling-the-creativity-deterministic-output-of-prompt-responses/172683)
             """
         gr.Markdown(dedent(_))
     chatbot = gr.Chatbot()