Update app.py

app.py

@@ -3,7 +3,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 import gradio as gr
 
-# Model identifier
+# Model name
 model_name = "Qwen/Qwen2.5-3B-Instruct"
 
 # Load tokenizer and model
@@ -18,21 +18,16 @@ model = AutoModelForCausalLM.from_pretrained(
     trust_remote_code=True,
 )
 
-# Chat function (no history used for simplicity and compatibility)
+# Chat function
 def respond(message, history):
     messages = [{"role": "user", "content": message}]
-    
-    # Apply chat template
     prompt = tokenizer.apply_chat_template(
         messages,
         tokenize=False,
         add_generation_prompt=True
     )
-    
-    # Tokenize
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 
-    # Generate
     with torch.no_grad():
         outputs = model.generate(
             **inputs,
@@ -42,24 +37,23 @@ def respond(message, history):
             do_sample=True,
             pad_token_id=tokenizer.eos_token_id,
         )
-    
-    # Decode response
     response = tokenizer.decode(
-        outputs[0][inputs['input_ids'].shape[-1]:],
+        outputs[0][inputs["input_ids"].shape[-1]:],
         skip_special_tokens=True
     )
     return response
 
-# Gradio Interface — NO retry_btn / undo_btn (to avoid version issues)
+# Create Gradio ChatInterface
+# Gradio 3.50.2 supports ChatInterface fully
 demo = gr.ChatInterface(
     fn=respond,
-    title="Qwen2.5-3B-Instruct Chatbot",
-    description="Ask me anything! I'm a 3B AI assistant by Alibaba Cloud.",
+    title="Qwen2.5-3B Chatbot",
+    description="Ask me anything! I'm a smart AI assistant by Alibaba Cloud.",
     examples=[
-        "Explain quantum computing in simple terms.",
-        "Write a Python function to check if a number is prime.",
-        "Solve: 3x + 5 = 17"
-    ],
+        "Explain relativity in simple terms.",
+        "Write a Python function to reverse a string.",
+        "Solve: 2x + 8 = 20"
+    ]
 )
 
 # Launch