uie-m-large微调的问题

[zlw18813081566]

使用uie-m-large微调后的模型怎么用taskflow调用
直接使用报错

Traceback (most recent call last):
File "test.py", line 3, in
ie = Taskflow('information_extraction', schema=schema, task_path="./checkpoint/model_best/checkpoint-10000")
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddlenlp/taskflow/taskflow.py", line 516, in init
**self.kwargs)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddlenlp/taskflow/information_extraction.py", line 361, in init
self._get_inference_model()
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddlenlp/taskflow/task.py", line 228, in _get_inference_model
self._construct_model(self.model)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddlenlp/taskflow/information_extraction.py", line 419, in _construct_model
model_instance = UIE.from_pretrained(self._task_path)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddlenlp/transformers/model_utils.py", line 319, in from_pretrained
cls.base_model_class.name)
AssertionError: pretrained base model should be ErnieModel

[linjieccc]

@zlw18813081566 Hi,

可以试试指定下model为uie-m-large

ie = Taskflow("information_extraction", schema=schema, model="uie-m-large", task_path="./checkpoint/model_best/checkpoint-10000")

[zlw18813081566]

谢谢，解决了