Update app.py

app.py

@@ -42,7 +42,7 @@ model = PeftModel.from_pretrained(base_model, LORA_MODEL_PATH)
 model = model.to("cuda" if torch.cuda.is_available() else "cpu")
 
 # 定义推理函数
-@spaces.GPU(duration=2)
+@spaces.GPU(duration=10)
 def stream_chat(message: str, history: list, temperature: float, max_new_tokens: int, top_p: float, top_k: int, penalty: float):
     conversation = []
     for prompt, answer in history: