# Dongxi NLP explains LoRA and QLoRA through rank, low-rank approximation, and quantization

> Original title: 后训练文章系列第三篇，关于 LoRA 和 QLoRA

- Source: Dongxi NLP
- Published: 2026-10-24T09:01:52.000Z
- Bad Influence: https://badinfluence.news/items/aplpr4rde41av16vpoyjhvu2q
- Original: https://x.com/dongxi_nlp/status/2113918890753302818

## Summary

Dongxi NLP publishes the third post in its post-training series, covering LoRA and QLoRA. The post defines three core concepts, rank, low-rank approximation, and quantization, and links them through the idea of patterns in matrices.

## Post

后训练文章系列第三篇，关于 LoRA 和 QLoRA  

三个重要的基本概念：
 
rank 秩 
low-rank approximation 低秩近似 
quantization 量化  

它们可以用同一个概念串起来，即矩阵中的 pattern模式。

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2113918869270089728%2Fimg%2F9QVNKTYeb_o3ITHG.jpg&mode=thumb&exp=1793404800&sig=c1c9f17f29e90780)

## Quoted post @dongxi_nlp

> https://x.com/i/article/2113912265061593088

https://x.com/dongxi_nlp/status/2113917090503516270