Update app.py

app.py

@@ -20,7 +20,7 @@ Follow these steps:
 [Reason]: Execute plan with detailed analysis
 [Verify]: Check logic and evidence
 [Conclude]: Present structured conclusion
-You are allowed to use code to think amd answer better, Ensure maximum accuracy 
+You are allowed to use code to think amd answer better.
 
 """
 
@@ -59,8 +59,9 @@ def initialize_model():
 def format_response(text):
     return text.replace("[Understand]", '\n<strong class="special-tag">[Understand]</strong>\n') \
               .replace("[Plan]", '\n<strong class="special-tag">[Plan]</strong>\n') \
-              .replace("[Conclude]", '\n<strong class="special-tag">[Conclude]</strong>\n')
-
+              .replace("[Conclude]", '\n<strong class="special-tag">[Conclude]</strong>\n') \
+              .replace("[Reason]", '\n<strong class="special-tag">[Reason]</strong>\n') \
+              .replace("[Verify]", '\n<strong class="special-tag">[Verify]</strong>\n')
 @spaces.GPU
 def generate_response(message, chat_history, system_prompt, temperature, max_tokens):
     # Create conversation history for model
@@ -120,7 +121,7 @@ with gr.Blocks(css=CSS, theme=gr.themes.Soft()) as demo:
     
     with gr.Accordion("⚙️ Settings", open=False):
         system_prompt = gr.TextArea(value=DEFAULT_SYSTEM_PROMPT, label="System Instructions")
-        temperature = gr.Slider(0, 1, value=0.7, label="Creativity")
+        temperature = gr.Slider(0, 1, value=0.5, label="Creativity")
         max_tokens = gr.Slider(128, 4096, value=2048, label="Max Response Length")
 
     clear = gr.Button("Clear History")