Update app.py

app.py

@@ -7,7 +7,7 @@ client = Cerebras(
 )
 
 TTILE = """
-<h1 align="center">Try the world's fastest inference 🚀</h1>
+<h1 align="center">🚀 Try the world's fastest inference by Cerebras ⚡</h1>
 """
 NOTICE = """
 Current only support Llama3.1 8B and Llama 3.1 70B.
@@ -17,11 +17,12 @@ def respond(
     message,
     history: list[tuple[str, str]],
     model_id,
+    system_message,
     max_tokens,
     temperature,
     top_p,
 ):
-    messages = []
+    messages = [{"role": "system", "content": system_message}]
     
     for val in history:
         if val[0]:
@@ -56,6 +57,7 @@ chatbot = gr.ChatInterface(
             value="llama3.1-8b",
             label="Models"
         ),
+        gr.Textbox(value="You are a friendly assistant.", label="System message"),
         gr.Slider(minimum=1, maximum=8192, value=4096, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(