metadata

language:
  - bo
tags:
  - tibetan
  - masked-lm
base_model: Pagewood/Tibetan-BERT-wwm
license: apache-2.0
pipeline_tag: fill-mask
mask_token: '[MASK]'

bert-base-tibetan

Model Description

This is a BERT model pre-trained on Tibetan texts, derived from Tibetan-BERT-wwm with the tokenizer refined for PyTorch. You can fine-tune bert-base-tibetan 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/bert-base-tibetan")
model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/bert-base-tibetan")