transformers/model_cards/DeepPavlov/bert-base-bg-cs-pl-ru-cased
2020-07-15 18:59:20 +02:00
..
README.md [model_cards] Switch all languages codes to ISO-639-{1,2,3} 2020-07-15 18:59:20 +02:00

language
bg
cs
pl
ru

bert-base-bg-cs-pl-ru-cased

SlavicBERT[1] Slavic \(bg, cs, pl, ru, cased, 12layer, 768hidden, 12heads, 180M parameters) was trained on Russian News and four Wikipedias: Bulgarian, Czech, Polish, and Russian. Subtoken vocabulary was built using this data. Multilingual BERT was used as an initialization for SlavicBERT.

1