# --------------------------------------------
# CITATION file created with {cffr} R package
# See also: https://docs.ropensci.org/cffr/
# --------------------------------------------
 
cff-version: 1.2.0
message: 'To cite package "wordpiece.data" in publications use:'
type: software
license: Apache-2.0
title: 'wordpiece.data: Data for Wordpiece-Style Tokenization'
version: 2.0.0
doi: 10.32614/CRAN.package.wordpiece.data
abstract: Provides data to be used by the wordpiece algorithm in order to tokenize
  text into somewhat meaningful chunks. Included vocabularies were retrieved from
  <https://huggingface.co/bert-base-cased/resolve/main/vocab.txt> and <https://huggingface.co/bert-base-uncased/resolve/main/vocab.txt>
  and parsed into an R-friendly format.
authors:
- family-names: Bratt
  given-names: Jonathan
  email: jonathan.bratt@macmillan.com
  orcid: https://orcid.org/0000-0003-2859-0076
- family-names: Harmon
  given-names: Jon
  email: jonthegeek@gmail.com
  orcid: https://orcid.org/0000-0003-4781-4346
repository: https://jonthegeek.r-universe.dev
repository-code: https://github.com/macmillancontentscience/wordpiece.data
commit: f893df5061be8f53fd586b142274b7ed669112c9
url: https://github.com/macmillancontentscience/wordpiece.data
contact:
- family-names: Harmon
  given-names: Jon
  email: jonthegeek@gmail.com
  orcid: https://orcid.org/0000-0003-4781-4346