model1 = BertForMultiHopQuestionAnswering.from_pretrained(BERT_MODEL, cache_dir=PYTORCH_PRETRAINED_BERT_CACHE / 'distributed_{}'.format(-1))

[ShaoaAllen]

Model name 'bert-base-uncased' was not found in model name list (bert-base-uncased, bert-large-uncased, bert-base-cased, bert-large-cased, bert-base-multilingual-uncased, bert-base-multilingual-cased, bert-base-chinese). We assumed 'https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased.tar.gz' was a path or url but couldn't find any file associated to this path or url.

作者老师您好！ Model name 'bert-base-uncased' was not found in model name list (bert-base-uncased, 这个是我今年见过的最离谱的bug了。。。

[Sleepychord]

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?

[ShaoaAllen]

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