Update app.py

app.py

@@ -9,7 +9,10 @@ client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 def respond(
     message,
     history: list[tuple[str, str]],
-    system_message
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
 ):
 
     messages = [{"role": "system", "content": system_message}]
@@ -26,7 +29,10 @@ def respond(
 
     for message in client.chat_completion(
         messages,
-        stream=True
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
     ):
         token = message.choices[0].delta.content
 
@@ -39,7 +45,16 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message")
+        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)",
+        ),
     ],
 )