cjvt
/

t5-sl-large

t5-sl-large model is a Slovene T5 model. It has 24 encoder and 24 decoder layers, in total about 750 million parameters. It was trained for 3 epochs on the following corpora:

Corpora

The following corpora were used for training the model:

  • Gigafida 2.0
  • Kas 1.0
  • Janes 1.0 (only Janes-news, Janes-forum, Janes-blog, Janes-wiki subcorpora)
  • Slovenian parliamentary corpus siParl 2.0
  • slWaC

Evaluation

The model is described in detail and evaluated in our paper "Sequence to sequence pretraining for a less-resourced Slovenian language"

Downloads last month
21
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.