v1.1, October 2026. Read-or-Think: one-pass answer, a short thought only when unsure. 4B, 9B, 27B.
AI & ML interests
None defined yet.
Recent Activity
Papers
DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems
StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions
v1.1, October 2026. Typed decisions in one forward pass: a probability for every option. 0.8B to 27B.
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 • 23 -
startlux-models/gdn-340m-pas-fa-layer12-10b
Text Generation • 0.4B • Updated • 19 -
startlux-models/gdn-340m-pas-fa-layer20-10b
Text Generation • 0.4B • Updated • 18 -
startlux-models/gdn-nooutgate-340m-pas-fa-layer12-10b
Text Generation • 0.4B • Updated • 16
v1.1, October 2026. Read-or-Think: one-pass answer, a short thought only when unsure. 4B, 9B, 27B.
v1.1, October 2026. Typed decisions in one forward pass: a probability for every option. 0.8B to 27B.
Typed decision models from 0.8B to 27B. Every question comes back with a probability for each option.
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 • 23 -
startlux-models/gdn-340m-pas-fa-layer12-10b
Text Generation • 0.4B • Updated • 19 -
startlux-models/gdn-340m-pas-fa-layer20-10b
Text Generation • 0.4B • Updated • 18 -
startlux-models/gdn-nooutgate-340m-pas-fa-layer12-10b
Text Generation • 0.4B • Updated • 16