Beyond IceBERT: Open-Data ModernBERT Encoders for Icelandic from 12M to 1B Parameters Paper • 2610.36230 • Published 14 days ago
Multilingual GSM-Symbolic: What determines capability transfer across languages? Paper • 2610.03367 • Published Oct 2 • 23
A Warm Start and a Clean Crawled Corpus -- A Recipe for Good Language Models Paper • 2201.05601 • Published Jan 14, 2022
Global PIQA: Evaluating Physical Commonsense Reasoning Across 100+ Languages and Cultures Paper • 2510.24081 • Published Oct 28, 2025 • 24
Icelandic ModernBERT Collection Icelandic ModernBERT encoders, 12M to 1B parameters, trained on open data: the size ladder and the warm-start study. MIT licence. • 35 items • Updated 11 days ago