specific method · filed under model architecture
RoPE with attention sink
A configuration combining RoPE with an attention sink, described as a possible replacement for a sliding window.
Also called RoPE + attention sink.
- 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 :: softmax attention :: attention sink.