RoPE 位置编码算法详解 - Zhang #194
Replies: 1 comment
-
|
试试评论功能! |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
RoPE 位置编码算法详解 - Zhang
从事 LLM 推理部署、视觉算法开发、模型压缩部署以及算法SDK开发工作,终身学习践行者。Transformer旋转位置编码(Rotary Position Embedding,RoPE)是论文 Roformer Enhanced Transformer With Rotray Position Embedding 提出的一种能够将相对位置信息依赖集成到 self-attention 中并提升 transformer 架构性能的位置编码方式。
https://harleyszhang-github-io.vercel.app/2024-10-27/rope.html
Beta Was this translation helpful? Give feedback.
All reactions