README.md

metadata

language:
  - be
tags:
  - belarusian
  - masked-lm
license: cc-by-sa-4.0
datasets:
  - statmt/cc100
  - wikimedia/wikipedia
pipeline_tag: fill-mask
mask_token: '[MASK]'

deberta-base-belarusian

Model Description

This is a DeBERTa(V2) model pre-trained on Belarusian Wikipedia and CC-100 texts. You can fine-tune deberta-base-belarusian for downstream tasks, such as POS-tagging, dependency-parsing, and so on.

How to Use

from transformers import AutoTokenizer,AutoModelForMaskedLM
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/deberta-base-belarusian")
model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/deberta-base-belarusian")