[Question]: 使用Taskflow 加载 官方以及自己训练出来的uie-m-large模型都报错

[526872163]

请提出你的问题

Traceback (most recent call last): File "C:\tender\main.py", line 43, in ie = Taskflow('information_extraction', schema=schema, position_prob=0.3, File "C:\Users\Administrator\anaconda3\envs\tender\lib\site-packages\paddlenlp\taskflow\taskflow.py", line 837, in init self.task_instance = task_class( File "C:\Users\Administrator\anaconda3\envs\tender\lib\site-packages\paddlenlp\taskflow\information_extraction.py", line 536, in init self._get_inference_model() File "C:\Users\Administrator\anaconda3\envs\tender\lib\site-packages\paddlenlp\taskflow\task.py", line 366, in _get_inference_model self._prepare_static_mode() File "C:\Users\Administrator\anaconda3\envs\tender\lib\site-packages\paddlenlp\taskflow\task.py", line 221, in _prepare_static_mode self.predictor = paddle.inference.create_predictor(self._config) RuntimeError: (Unavailable) An error occurred while loading model parameters. Please check whether the model file is complete or damaged. [Hint: Expected static_cast(*buffer) == true, but received static_cast(*buffer):0 != true:1.] (at ..\paddle/fluid/operators/load_combine_op.h:86) [operator < load_combine > error]

Process finished with exit code 1

报错如上，使用了两台电脑测试遇到一样的问题，win10系统，paddlepadle-gpu 试过2.4以及2.32，cuda11.7和11.6，paddlenlp版本2.5.2 post0，内存一台32G，一台128G，显卡：3090

[526872163]

使用uie-base模型是正常的

[FlyDut]

有解决方法吗？