---
title: "Discussion on \"Rotary Positional Embeddings, Worked Through in NumPy\" | Hashnode"
description: "Discussion on \"Rotary Positional Embeddings, Worked Through in NumPy\". Most explanations of rotary positional embeddings stop at the formula. A query vector gets rotated by an angle that depends on its position, a key vector gets rotated by its own angle, and the dot pro"
url: "https://hashnode.com/posts/rotary-positional-embeddings-worked-through-in-numpy/6afa4ff9652ff2f99b6372ee"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Rotary Positional Embeddings, Worked Through in NumPy](https://aheadkit.hashnode.dev/rotary-positional-embeddings-worked-through-in-numpy?utm_source=hashnode&utm_medium=feed)

Most explanations of rotary positional embeddings stop at the formula. A query vector gets rotated by an angle that depends on its position, a key vector gets rotated by its own angle, and the dot pro

22h ago · 9 min read · aheadkit.hashnode.dev  
Read the article

-   [#numpy](https://hashnode.com/tag/numpy)
-   [#machine-learning](https://hashnode.com/tag/machine-learning)
-   [#transformers](https://hashnode.com/tag/transformers)
-   [#python](https://hashnode.com/tag/python)

## Written by

[Abdus Salam](https://hashnode.com/@aheadkit)

@aheadkit

  
[View profile](https://hashnode.com/@aheadkit)

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
