moBERTo - a Tropic-AI Collection

Tropic-AI 's Collections

moBERTo

updated 1 day ago

Portuguese adaptation of ModernBERT, obtained through continued pretraining on a curated 12-billion-token Portuguese corpus

Tropic-AI/moBERTo

Fill-Mask • 0.1B • Updated 1 day ago • 5
Tropic-AI/moBERTo-orig-tokenizer

Fill-Mask • 0.1B • Updated 1 day ago • 11
Tropic-AI/moberto-pretraining-dataset-c4-compatible

Viewer • Updated 1 day ago • 11.4M • 174
moBERTo: A Modern Encoder for Portuguese via Continued Pretraining of ModernBERT

Paper • 2606.22722 • Published 4 days ago • 1