raduion's picture
Create README.md
ec2adc0
|
raw
history blame
242 Bytes
## BERT Medium for Luxembourgish
Created from a dataset with 1M Luxembourgish sentences from Wikipedia. Corpus has approx. 16M words.
MLM objective was trained.
The BERT model has parameters `L=8` and `H=512`.
Vocabulary has 70K word pieces.