loaders.md
In wordpiece.data: Data for Wordpiece-Style Tokenization

uncased vocab works

Code
  head(test_result, 5)
Output
  [1] "[PAD]"     "[unused0]" "[unused1]" "[unused2]" "[unused3]"

Code
  head(test_result, 5)
Output
  [1] "[PAD]"     "[unused1]" "[unused2]" "[unused3]" "[unused4]"

Any scripts or data that you put into this service are public.

wordpiece.data documentation built on March 18, 2022, 7:26 p.m.

Note that we can't provide technical support on individual packages. You should contact the package authors for that.