Update app.py

app.py

@@ -43,7 +43,6 @@ def load_model():
         
         print("Model loaded successfully!")
 
-@spaces.GPU(duration=120)
 def chat_response(message, history, character_name="珞璃", max_tokens=512, temperature=0.7, top_p=0.9):
     """Generate chat response using the loaded model"""
     global model, tokenizer
@@ -105,7 +104,6 @@ def chat_response(message, history, character_name="珞璃", max_tokens=512, tem
         print(f"Error during generation: {e}")
         return f"Sorry, I encountered an error: {str(e)}"
 
-@spaces.GPU(duration=120)
 def chat_response_streaming(message, history, character_name="珞璃", max_tokens=512, temperature=0.7, top_p=0.9):
     """Generate streaming chat response"""
     global model, tokenizer
@@ -253,6 +251,7 @@ def create_interface():
                 )
         
         # Event handlers
+        @spaces.GPU(duration=30)
         def respond(message, chat_history, char_name, max_tok, temp, top_p_val, use_streaming):
             if use_streaming:
                 # For streaming response - add user message first