IceBERT

IceBERT was trained with fairseq using the RoBERTa model on the Icelandic Giga Word corpus.

This model will soon be replaced with another version trained on a larged dataset, this model will then be renamed to IceBERT-IGC

Downloads last month
1,883
Hosted inference API
Fill-Mask
Mask token: <mask>
This model can be loaded on the Inference API on-demand.