Update app.py

app.py

@@ -8,17 +8,19 @@ HEADERS = {"Authorization": f"Bearer {HF_TOKEN}"}
 zephyr_7b_beta = "https://api-inference.huggingface.co/models/HuggingFaceH4/zephyr-7b-beta/"
 
 welcome_message = """
-Hi! I'll help you **build a GPT**. You can say something like, "make a bot that gives advice on how to grow your startup."
-What would you like to make?
+Hi! I'll help you **build a GPT.** You can say something like, "make a bot that gives advice on how to grow your startup." What would you like to make?
 """
 
 zephyr_system_prompt = """
 You are an AI whose job it is to help users create their own chatbots. In particular, you need to respond succinctly in a friendly tone, write a system prompt for an LLM, a catchy title for the chatbot, and a very short example user input. Make sure each part is included.
+
 For example, if a user says, "make a bot that gives advice on how to grow your startup", first do a friendly response, then add the title, system prompt, and example user input. Immediately STOP after the example input. It should be EXACTLY in this format:
+
 Sure, I'd be happy to help you build a bot! I'm generating a title, system prompt, and an example input. How do they sound? Feel free to give me feedback!
 Title: Startup Coach
 System prompt: Your job as an LLM is to provide good startup advice. Do not provide extraneous comments on other topics. Be succinct but useful. 
 Example input: Risks of setting up a non-profit board
+
 Here's another example. If a user types, "Make a chatbot that roasts tech CEOs", respond: 
 Sure, I'd be happy to help you build a bot! I'm generating a title, system prompt, and an example input. How do they sound? Feel free to give me feedback!
 Title: Tech Roaster
@@ -73,3 +75,4 @@ st.markdown("You can build and test them for free, but will need a [HF Pro accou
 # Predict and display the response
 model_response = predict_beta(user_input)
 st.markdown(f"**Model Response:** {model_response}")
+