550952213 comments

Results 9 comments of

550952213

解决了。法1：降级pytorch==1.4.0 法2：extended_attention_mask = extended_attention_mask.to(dtype=next(self.parameters()).dtype) # fp16 compatibility 改成extended_attention_mask = extended_attention_mask.to(dtype=torch.float32) # fp16 compatibility 就是报错的最后一个。服务器的话，要在服务器上找到那个环境下改，我就是在本地改的，一直没映射上去

Didn't find file /pretrained_bert_models/bert-base-chinese/added_tokens.json. We won't load it. Didn't find file /pretrained_bert_models/bert-base-chinese/special_tokens_map.json. We won't load it. Didn't find file /pretrained_bert_models/bert-base-chinese/tokenizer_config.json. We won't load it.

这三个文件是啥啊啊啊啊啊

Didn't find file /pretrained_bert_models/bert-base-chinese/added_tokens.json. We won't load it. Didn't find file /pretrained_bert_models/bert-base-chinese/special_tokens_map.json. We won't load it. Didn't find file /pretrained_bert_models/bert-base-chinese/tokenizer_config.json. We won't load it.

not found in model shortcut 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, bert-base-german有哪位大佬能解释下，这些都是啥文件

550952213

你好，使用我的数据集测试存在一个问题

多GPU运行出错，

多GPU运行出错，

Didn't find file /pretrained_bert_models/bert-base-chinese/added_tokens.json. We won't load it. Didn't find file /pretrained_bert_models/bert-base-chinese/special_tokens_map.json. We won't load it. Didn't find file /pretrained_bert_models/bert-base-chinese/tokenizer_config.json. We won't load it.

Didn't find file /pretrained_bert_models/bert-base-chinese/added_tokens.json. We won't load it. Didn't find file /pretrained_bert_models/bert-base-chinese/special_tokens_map.json. We won't load it. Didn't find file /pretrained_bert_models/bert-base-chinese/tokenizer_config.json. We won't load it.

AssertionError: i is not a valid tag in encoding type:bmeso. Please check your encoding_type.

数据问题

论文是用jieba工具分词的吗？

如何添加自己的词向量？