Model techniques map
Techniquesmodel architecturepositional encoding

specific method · filed under model architecture

Rotary Position Embedding

A positional encoding that applies rotary transformations to attention representations; the supplied mentions also describe partial application in particular configurations.

Also called RoPE, Rotary Positional Embedding (RoPE), rotary position embeddings (RoPE), rotary position embeddings, Rotary Positional Embedding, Rotary positional embeddings.

sources
5
models
6
labs adopt it
5
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 5

Documented in

Evidence

5 spans quoted from the sources, strongest treatment first.

We apply rotary position embeddings [14]

usedmodel architecturein gpt-oss-120b and gpt-oss-20bOpenAI

RoPE dimension 64

usedmodel architecturein MiniMax Sparse AttentionMiniMax

we partially employ the Rotary Positional Embedding (RoPE) to the attention queries, KV entries, and the core attention outputs

usedmodel architecturein DeepSeek-V4DeepSeek

We employ Rotary Positional Encodings (RoPE) to encode positional information.

usedmodel architecturein Laguna XS.2Poolside

Rotary Positional Embedding (RoPE) is partially applied to the first 64 dimensions query and key

usedmodel architecturein MiMo-V2-FlashXiaomi

Filed alongside

Other methods under model architecture :: positional encoding.