stefan-it's picture
readme: add initial version
7f8255f
metadata
license: mit
language:
  - en
  - de
  - fr
  - fi
  - sv
  - nl

hmByT5 - Preliminary Language Models

Preliminary Historic Multilingual and Monolingual ByT5 Models. Following languages are currently covered:

  • English (British Library Corpus - Books)
  • German (Europeana Newspaper)
  • French (Europeana Newspaper)
  • Finnish (Europeana Newspaper)
  • Swedish (Europeana Newspaper)
  • Dutch (Delpher Corpus)

More details can be found in our GitHub repository.

In this experiment we sample 4B bytes (~4GB of text) from each corpora (and upsample Swedish and Finnish).

Pretraining

We use the official JAX/FLAX example in Hugging Face Transformers to pretrain a ByT5 model on a single v3-8 TPU. Details about the training can be found here.

Evaluation on Downstream Tasks (NER)

We evaluated the hmByT5 model on downstream tasks:

Model English AjMC German AjMC French AjMC Finnish NewsEye Swedish NewsEye Dutch ICDAR French ICDAR Avg.
hmbyt5-preliminary/byt5-small-multilingual-4g 83.49 ± 0.96 87.65 ± 0.63 84.16 ± 0.90

Acknowledgements

Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC). Many Thanks for providing access to the TPUs ❤️