Update app.py

app.py

@@ -1,3 +1,50 @@
 import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
-gr.load("models/Qwen/Qwen2.5-Coder-32B-Instruct").launch()
+def create_chat_interface():
+    # Initialize model and tokenizer
+    model_name = "Qwen/Qwen2.5-Coder-32B-Instruct"
+    tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+    model = AutoModelForCausalLM.from_pretrained(
+        model_name,
+        device_map="auto",
+        trust_remote_code=True
+    )
+
+    # Chat function
+    def chat(message, history):
+        # Format input with chat template
+        prompt = f"User: {message}\nAssistant:"
+        
+        # Generate response
+        inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=512,
+            temperature=0.7,
+            num_return_sequences=1
+        )
+        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        
+        return response
+
+    # Create Gradio interface
+    interface = gr.ChatInterface(
+        fn=chat,
+        title="Code Assistant Chat",
+        description="Ask coding questions or get help with programming tasks.",
+        theme=gr.themes.Soft(),
+        examples=[
+            "Write a Python function to sort a list",
+            "How do I read a CSV file in pandas?",
+            "Explain object-oriented programming concepts"
+        ]
+    )
+    
+    return interface
+
+if __name__ == "__main__":
+    # Launch the interface
+    chat_app = create_chat_interface()
+    chat_app.launch(share=True)