Update app.py

app.py

@@ -58,7 +58,7 @@ def stream_together_model(model_name, user_prompt, add_thinking_delay=False):
     if add_thinking_delay:
         # Add 4 second delay and yield thinking message
         yield "🤔 Thinking..."
-        time.sleep(4)
+        time.sleep(8)
         # Clear the thinking message
         yield ""
     
@@ -93,7 +93,7 @@ def stream_model_c(user_prompt, enable_thinking=True):
             {"role": "user", "content": user_prompt}
         ],
         "stream": True,
-        "max_tokens": 4096,
+        "max_tokens": 14096,
         "enable_thinking": enable_thinking  # Add thinking mode parameter
     }
     
@@ -328,8 +328,7 @@ h1 {
 with gr.Blocks(css=custom_css, theme=gr.themes.Base()) as demo:
     gr.HTML("""
         <div class="container">
-            <h1>Palmyra Multi-Model Chat</h1>
-            <p class="subtitle">Compare responses from DeepSeek, Llama, and Baseten models</p>
+            <h1>Palmyra-x5</h1>
         </div>
     """)