Kimi-Linear-A3B Collection Moonshot's experimental MoE model with Kimi Delta Attention • 3 items • Updated Jan 27 • 24
Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling Paper • 2604.28075 • Published Apr 30 • 20
Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling Paper • 2604.28075 • Published Apr 30 • 20