Update

app.py

@@ -292,23 +292,12 @@ with gr.Blocks(
         yield from bot_stream(chat_history, **config)
 
     with gr.Accordion("🎈 Info", open=False):
-        poundkey = "#"
         gr.Markdown(
             dedent(
                 f"""
                 ## {model_name.lower()}
 
-                * temperature range: .51 and up; higher temperature implies more random outputs. Suggested temperature for chatting and creative writing is around 1.1 while it should be set to 0.51-1.0 for summerizing and translation for example.
-
-                * Set `repetition_penalty` to 2.1 or higher for a chatty conversation (more unpredictable and undesirable output). Lower it to 1.1 or smaller if more focused anwsers are desired (for example for translations or fact-oriented queries).
-
-                * Smaller `top_k` probably will result in smoothier sentences.
-                (`top_k=0` is equivalent to `top_k` equal to very very big though.) Consult `transformers` documentation for more details.
-
-                * If you inadvertanyl messed up the parameters or the model, reset it in Advanced Options or reload the browser.
-
-                <p></p>
-                An api is available at, well, https://mikeee-qwen-7b-chat.hf.space/, e.g. in python
+                * temperature range: .51 and up; higher temperature implies more randomness. Suggested temperature for chatting and creative writing is around 1.1 while it should be set to 0.51-1.0 for summarizing https://mikeee-qwen-7b-chat.hf.space/ that can be queried, e.g. in python
 
                 ```python
                 from gradio_client import Client
@@ -316,19 +305,18 @@ with gr.Blocks(
                 client = Client("https://mikeee-qwen-7b-chat.hf.space/")
 
                 result = client.predict(
-                    "你好!",  {poundkey} user prompt
-                    256,  {poundkey} max_new_tokens
-                    1.2,  {poundkey} temperature
-                    1.1,  {poundkey} repetition_penalty
-                    0,  {poundkey} top_k
-                    0.9,  {poundkey} top_p
-                    "You are a help assistant",  {poundkey} system_prompt
-                    None,  {poundkey} history
+                    "你好!",  # user prompt
+                    256,  # max_new_tokens
+                    1.2,  # temperature
+                    1.1,  # repetition_penalty
+                    0,  # top_k
+                    0.9,  # top_p
+                    "You are a help assistant",  # system_prompt
+                    None,  # history
                     api_name="/api"
                 )
                 print(result)
                 ```
-
                 or in javascript
                 ```js
                 import {{ client }} from "@gradio/client";
@@ -337,12 +325,12 @@ with gr.Blocks(
                 const result = await app.predict("api", [...]);
                 console.log(result.data);
                 ```
-                Check documentation and examples by clicking `Use via API` at the very bottom of this page.
+                Check documentation and examples by clicking `Use via API` at the very bottom of [https://huggingface.co/spaces/mikeee/qwen-7b-chat](https://huggingface.co/spaces/mikeee/qwen-7b-chat).
 
                 <p></p>
                 Most examples are meant for another model.
                 You probably should try to test
-                some related prompts."""
+                some related prompts. System prompt can be changed in Advaned Options as well."""
             ),
             elem_classes="xsmall",
         )