specific method · filed under model architecture
Gated attention with partial RoPE
A gated-attention configuration that applies rotary position encoding partially, with the cited instance specifying 50%.
Also called Gated attention with partial RoPE (50%), + GA Partial RoPE (50%).
- source
- 1
- model
- 1
- labs adopt it
- 0
- strongest
- evaluated
How sources treat it
One count per evidence span, weakest treatment to strongest.
evaluated 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
+ GA Partial RoPE (50%)
evaluatedmodel architecturein Laguna XS.2Poolside
Filed alongside
Other methods under model architecture :: positional encoding.
YaRNRotary Position Embedding2D rotary position embeddingRoPE scalingLearned input-dependent relative position biasNo Position EncodingProportional Rotary Position EmbeddingRelative attention2D coordinate-based positional embeddingsOmitting RoPE in attention layersPartial RoPEPer-layer-type rotary position scalesTemporal-Modality Rotary Position Embedding