implementation detail · filed under model architecture
Dense Attention Fallback
Uses dense attention as a per-layer alternative to the sliding-window pattern.
Also called dense attention as a per-layer fallback.
- source
- 1
- model
- 1
- labs adopt it
- 0
- strongest
- unclear
How sources treat it
One count per evidence span, weakest treatment to strongest.
unclear 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
the sliding window is most likely replaced by RoPE + attention sink, or simply by dense attention as a per-layer fallback
unclearmodel architecturein MiniMax-M3MiniMax
Filed alongside
Other methods under model architecture :: token mixer :: hybrid layer stacking.
Hybrid AttentionMamba-2, Mixture-of-Experts, and Selective Attention HybridHybrid Mamba-TransformerHybrid Mamba-AttentionGated DeltaNet and Gated AttentionHybrid Mamba-Transformer Mixture-of-Experts Layer LayoutGated Attention and Sliding-Window Attention ConfigurationGated DeltaNet and Full AttentionGated DeltaNet and Qwen Sparse Attentionhybrid Gated DeltaNet + sparse MoE architectureHybrid sparse mixture-of-experts Transformer architectureSearch-Based Sliding-Window Attention Pattern