qhd0081
qhd0081
同问，似乎没办法使用pytorch版本的roberta tokenizer
> From the error message, it seems that the `transformers` and `sentence_transformers` packages used by your code are the ones installed in the python library (site-packages), rather than the modified...
> 您好，我这边有个小小的疑问，为什么单词节点不用glove之类的词向量进行初始化呢，您有做过相关的实验吗 我看了代码，好像所有的节点都是用BERT的表示作为初始化，这样词的节点表示永远为零。