Task
Fill Mask
This is a very small distilled version of the bert-base-multilingual-cased model for Russian and English (45 MB, 12M parameters). There is also an updated version of this model, rubert-tiny2, with a larger vocabulary and better quality on practically all Russian NLU tasks.
This is a very small distilled version of the bert-base-multilingual-cased model for Russian and English (45 MB, 12M parameters). There is also an updated version of this model, rubert-tiny2, with a larger vocabulary and better quality on practically all Russian NLU tasks.