Update app.py

app.py

@@ -1,20 +1,17 @@
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import gradio as gr
 
-# Load a lightweight model (CPU-friendly)
 model_name = "microsoft/DialoGPT-small"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
 
-# Store chat history per session using Gradio's state
 def predict(message, history):
-    # Format conversation for DialoGPT
+    # Build conversation context
     chat_history = ""
     for human, ai in history:
         chat_history += f"User: {human}\nBot: {ai}\n"
     chat_history += f"User: {message}\nBot:"
 
-    # Tokenize and generate
     inputs = tokenizer.encode(chat_history, return_tensors="pt")
     outputs = model.generate(
         inputs,
@@ -25,18 +22,13 @@ def predict(message, history):
         top_k=50
     )
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    
-    # Extract only the bot's latest reply
     bot_reply = response.split("Bot:")[-1].strip()
     return bot_reply
 
-# Launch the chat interface
+# Use only universally supported args
 gr.ChatInterface(
     fn=predict,
     title="💬 My Chatbot",
     description="A simple CPU-friendly chatbot using DialoGPT-small.",
     examples=["Hello!", "What's your name?", "Tell me a fun fact."],
-    retry_btn=None,
-    undo_btn=None,
-    clear_btn="Clear",
 ).launch()