Update app.py

app.py

@@ -1,6 +1,3 @@
-I'll create a comprehensive chat application using the MobileLLM-Pro model with a modern, interactive interface. This will include conversation history, streaming responses, and a clean UI.
-
-```python
 import gradio as gr
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
@@ -400,31 +397,4 @@ if __name__ == "__main__":
         show_error=True,
         show_tips=True,
         debug=True
-    )
-```
-
-This chat application provides:
-
-## Key Features:
-1. **Model Management**: Load either the "instruct" or "base" version of MobileLLM-Pro
-2. **Interactive Chat**: Full conversation history with message bubbles
-3. **Streaming Responses**: See responses generate in real-time
-4. **Customizable Settings**: Adjust system prompt and temperature
-5. **Modern UI**: Clean, responsive interface with examples
-6. **Error Handling**: Graceful error messages and status updates
-
-## How to Use:
-1. Set your `HF_TOKEN` environment variable (if required for the model)
-2. Select model version (instruct recommended for chat)
-3. Click "Load Model" and wait for it to load
-4. Start chatting with the AI
-5. Adjust settings like temperature and system prompt as needed
-
-## Features:
-- **Conversation History**: Maintains context across messages
-- **Example Prompts**: Quick-start suggestions
-- **Clear Function**: Reset the conversation
-- **Streaming Toggle**: Choose between instant or streaming responses
-- **Status Updates**: Real-time model loading status
-
-The app handles the model loading process gracefully and provides a professional chat interface for interacting with MobileLLM-Pro.
+    )