Update app.py

app.py

@@ -5,10 +5,14 @@
 
 # %%writefile demo-4bit.py
 
+from textwrap import dedent
+
 from transformers import AutoModel, AutoTokenizer
 import gradio as gr
 import mdtex2html
 
+# from loguru import logger
+
 model_name = "THUDM/chatglm2-6b"
 model_name = "THUDM/chatglm2-6b-int4"
 
@@ -33,7 +37,6 @@ model = model.eval()
 
 _ = """Override Chatbot.postprocess"""
 
-
 def postprocess(self, y):
     if y is None:
         return []
@@ -100,9 +103,22 @@ def reset_state():
     return [], [], None
 
 
-with gr.Blocks() as demo:
+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 
+            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
+
+            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
+            """
+        gr.Markdown(dedent(_))
     chatbot = gr.Chatbot()
     with gr.Row():
         with gr.Column(scale=4):