architecture

Definition

The structural design of a model — what layers exist, how they connect, where information is allowed to flow. Named architectures such as the Transformer or Mixture-of-Experts determine what a model can represent and, just as importantly, how efficiently it maps onto hardware. Keep it distinct from the trained model: the architecture is the shape, the weights are what fill it, and one architecture can host very different systems.

Explainers using this term

• Paper Walkthrough: Designing Qwen3.8-Next — Accuracy, Efficiency and Stability as One ProblemOn the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability
• Paper Walkthrough: GigaBrain-0.7 — 37,000 Hours of Embodied Experience and a Three-System Robot BrainGigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture