20260617:目前有914 页
This commit is contained in:
38
concepts/lora.md
Normal file
38
concepts/lora.md
Normal file
@@ -0,0 +1,38 @@
|
||||
---
|
||||
title: "LoRA (Low-Rank Adaptation)"
|
||||
created: 2026-06-01
|
||||
updated: 2026-06-01
|
||||
type: concept
|
||||
tags: [fine-tuning, peft, llm]
|
||||
sources: [raw/papers/xu-why-steering-works-2026.md]
|
||||
confidence: medium
|
||||
---
|
||||
|
||||
# LoRA(低秩适配)
|
||||
|
||||
## 定义
|
||||
|
||||
LoRA(Low-Rank Adaptation, Hu et al., 2022)是一种参数高效微调方法,通过冻结原始权重 $W$ 并训练低秩更新 $\Delta W = BA$($B \in \mathbb{R}^{d \times r}, A \in \mathbb{R}^{r \times k}, r \ll \min(d,k)$)来适配模型。
|
||||
|
||||
推理时:$W \leftarrow W + \Delta W = W + BA$
|
||||
|
||||
## 在统一动态权重视角中
|
||||
|
||||
在 Xu et al. (2026) 的统一框架中,带缩放系数的 LoRA 表达为:
|
||||
|
||||
$$h_{i+1} = (W + mBA)h_i + b$$
|
||||
|
||||
$$\Delta h = m(BA h_i)$$
|
||||
|
||||
LoRA 是**仅修改 W**(不修改 b)的动态权重更新,参数规模为 $d_{in} \times r + r \times d_{out}$。
|
||||
|
||||
## 导向动态
|
||||
|
||||
LoRA 与其他干预形式一样呈现三阶段偏好动态和效用衰减,其表现与 Local Weight 方法高度一致。
|
||||
|
||||
## 相关概念
|
||||
|
||||
- [[dynamic-weight-updates]] — 统一框架中的 LoRA 位置
|
||||
- [[activation-steering]] — b-only 的动态更新
|
||||
- [[steering-dynamics]] — LoRA 的偏好-效用动态
|
||||
- [[xu-why-steering-works]] — 源论文
|
||||
Reference in New Issue
Block a user