change layout and readme

app.py

@@ -105,8 +105,8 @@ with gr.Blocks(gr.themes.Soft(), js=js_code_label, css=custom_css) as demo:
                             stop_btn = gr.Button("Stop")
                             clear_btn = gr.Button("Clear")
     with gr.Row():
-        chat_a = gr.Chatbot(height=500, label="Nudging Answer", elem_id="chatbot")
         chat_b = gr.Chatbot(height=500, label="Base Answer")
+        chat_a = gr.Chatbot(height=500, label="Nudging Answer", elem_id="chatbot")
         
     base_model_choice.value = "Llama-2-70B"
     nudging_model_choice.value = "Llama-2-13B-chat"

constant.py

@@ -4,7 +4,7 @@ HEADER_MD = """# Inference-time Alignment with Nudging.
 **By injecting a few nudging tokens at inference time, we can make base models able to follow user instructions helpfully and safely.** 
 - Our demo is powered by the [Together AI API](https://api.together.ai/). However, since only three base models are currently still available in the serverless API, we only choose three base models and nudging models for demonstration.
 - The daily limit is 50 requests per IP address. If you need more, please contact us.
-
+- This demo uses an API-based implementation of the nudging, which can be slow due to multiple API calls for each question. With a proper speculative decoding type implementation, the inference speed of nudging can be significantly improved.
 """
 
 js_code_label = """