RikkaBotan/NexteraBERT-Mezzoforte-220M-en
Fill-Mask • 0.2B • Updated • 404 • 15
NexteraBERT
Input-Dependent Gating Liquid Mixer and Length-Adaptive Attention for Fast, Long-Context Bidirectional Encoders
Input-Dependent Gating Liquid Mixer and Length-Adaptive Attention for Fast, Long-Context Bidirectional Encoders