llll

Hello,author! It is a good work but i have a question about the language model. Why the language_model(pretrain Bert)'s text input is tokenized by your paper's vocabulary(size is 10201)rather than...

question about CUDA memory for SCST

5

Hello！Author! I want to reproduce your experimental code，but when i run code for SCST, it occures 'cuda out of memory'. I want to know how much CUDA memory is needed...