Hi, I tried to run this code but encountered one problem: there are several special tokens such as "<#Q2K#>", "<#K#>", and "<#Q#>" after bert tokenization, however, the original bert vocab does not contain these three tokens, which caused the tokenization indexing error. How did you solve this issue? Thanks!
Hi, I tried to run this code but encountered one problem: there are several special tokens such as "<#Q2K#>", "<#K#>", and "<#Q#>" after bert tokenization, however, the original bert vocab does not contain these three tokens, which caused the tokenization indexing error. How did you solve this issue? Thanks!