yhcc / BARTNER

215 stars 22 forks source link

Migrate to transformers 4.0.0 or above? #16

Open kizunasunhy opened 2 years ago

kizunasunhy commented 2 years ago

Hello! I'm using this model architecture to do NER on domain specific tasks and it worked pretty well! However the old version of transformer is still a little bit troublesome.

For example, in order to be close to the pretraining process of BART, I want to directly encode the whole sentence using the tokenizer, rather than split it by space and then using 'add_prefix_space=True'. So I tried the 'span' method successfully. But for 'word' method it will need extra work to do that because of the old version of tokenizer.

Is there any plan to release a transformer 4.0.0 (or above) version?