Update app.py

app.py

@@ -1,3 +1,4 @@
+!pip install gradio 
 import gradio as gr
 from huggingface_hub import InferenceClient
 
@@ -29,10 +30,10 @@ def respond(
 
     for message in client.chat_completion(
         messages,
-        max_tokens=max_tokens,
+        max_tokens=600,
         stream=True,
-        temperature=temperature,
-        top_p=top_p,
+        temperature=0.7,
+        top_p=0.95,
     ):
         token = message.choices[0].delta.content
 
@@ -44,22 +45,8 @@ def respond(
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
 demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+    respond,)
 
 
 if __name__ == "__main__":
-    demo.launch()
-    
+    demo.launch()