model1 = BertForMultiHopQuestionAnswering.from_pretrained(BERT_MODEL, cache_dir=PYTORCH_PRETRAINED_BERT_CACHE / 'distributed_{}'.format(-1)) about cogqa HOT 2 OPEN

I'm sorry but I have no idea about the bug with such a strange log. Could you check the network, version and path (or something like them) again?

from cogqa.

自己来回答下吧！这个问题算是有些眉目了！初步推测问题出在from pytorch_pretrained_bert.modeling import (
BertPreTrainedModel as PreTrainedBertModel, # The name was changed in the new versions of pytorch_pretrained_bert这句代码上，我尝试把as PreTrainedBertModel删了，然后BertForMultiHopQuestionAnswering(BertPreTrainedModel)再改下。
我猜测是BertPreTrainedModel这个类名字变化引起model1没有加载到

from cogqa.