Update app.py

app.py

@@ -1,4 +1,4 @@
-# 0. Install custom transformers and imports
+# 0. Install custom transformers and import packages
 import os
 os.system("pip install git+https://github.com/shumingma/transformers.git")
 
@@ -15,7 +15,7 @@ from transformers import (
 import gradio as gr
 import spaces
 
-# 1. System prompt (your original one)
+# 1. System prompt for Café Eleven
 SYSTEM_PROMPT = """
 You are a friendly café assistant for Café Eleven. Your job is to:
 1. Greet the customer warmly
@@ -27,10 +27,9 @@ You are a friendly café assistant for Café Eleven. Your job is to:
 Always be polite and helpful!
 """
 
-# 2. Model info
 MODEL_ID = "microsoft/bitnet-b1.58-2B-4T"
 
-# 3. Load model and tokenizer
+# 2. Load tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
@@ -40,7 +39,7 @@ model = AutoModelForCausalLM.from_pretrained(
 
 print(f"Model loaded on device: {model.device}")
 
-# 4. Respond function
+# 3. Response generation with streaming
 @spaces.GPU
 def respond(
     message: str,
@@ -50,9 +49,6 @@ def respond(
     temperature: float,
     top_p: float,
 ):
-    """
-    Generate a chat response using streaming with TextIteratorStreamer.
-    """
     messages = [{"role": "system", "content": system_message}]
     for user_msg, bot_msg in history:
         if user_msg:
@@ -85,7 +81,7 @@ def respond(
         response += new_text
         yield response
 
-# 5. Gradio UI
+# 4. Gradio ChatInterface setup
 demo = gr.ChatInterface(
     fn=respond,
     title="Café Eleven Assistant",
@@ -135,6 +131,6 @@ demo = gr.ChatInterface(
     ],
 )
 
-# 6. Launch
+# 5. Launch normally
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860)
+    demo.launch()