[KongchangAI]
Unverified50% confidenceFactExact time

LoRA 由 Hu 等人在 2021 年提出,通过为每层注入可训练的低秩分解矩阵实现参数更新 ΔW = BA,将可训练参数量压缩至原始模型的 0.1%-1%

1
Sources
50%
Confidence
Long-term
Relevance
8/25/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/798531
API
curl https://kongchang.com/api/v1/knowledge/claims/798531
MCP
get_claim(id=798531)