Official PAS, ISP, gating-ablation, and scale-study checkpoints for Massive Activations in Hybrid Linear Attention Models.
-
startlux-models/gdn-340m-pas-fa-layer04-10b
Text Generation • 0.4B • Updated -
startlux-models/gdn-340m-pas-fa-layer12-10b
Text Generation • 0.4B • Updated -
startlux-models/gdn-340m-pas-fa-layer20-10b
Text Generation • 0.4B • Updated -
startlux-models/gdn-nooutgate-340m-pas-fa-layer12-10b
Text Generation • 0.4B • Updated