模型无法导入

[zhangxinpe]

你好，我是分别从pip以及源码安装的，尝试了不同的版本，但是load roberta模型时都报错，请问是不是roberta模型还是不能用呢
dep_parser=None
con_parser = None
from tqdm import tqdm
from supar import Parser
if dep_parser is None:
dep_parser = Parser.load('biaffine-dep-roberta-en')
if con_parser is None:
con_parser = Parser.load('crf-con-en')

File c:\Users\b418\anaconda3\envs\learn\lib\site-packages\torch\serialization.py:1097, in load(f, map_location, pickle_module, weights_only, mmap, **pickle_load_args)
1095 except RuntimeError as e:
1096 raise pickle.UnpicklingError(_get_wo_message(str(e))) from None
-> 1097 return _load(
1098 opened_zipfile,
1099 map_location,
1100 pickle_module,
1101 overall_storage=overall_storage,
1102 **pickle_load_args,
...
1513 pass
1514 mod_name = load_module_mapping.get(mod_name, mod_name)
-> 1515 return super().find_class(mod_name, name)

ModuleNotFoundError: No module named 'supar.config'
Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings...