返回全部动态
ShadowPEFT 正式加入 Hugging Face PEFT 库
原标题：What If the Adaptation Were a Model? ShadowPEFT in 🤗 PEFT library
AI 摘要
Hugging Face 的 PEFT 库正式将 ShadowPEFT 纳入为一等方法。ShadowPEFT 与 LoRA 的适配器几何结构根本不同，但共用 get_peft_model 入口和适配器保存/加载路径。它引入一个带持久隐藏状态的有状态影子模型，在每层进行影子注入、基础编码和影子更新，实现跨层协调，并让任务特定组件成为可独立推理的模型。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
This article is also available in Chinese 简体中文 ShadowPEFT is now a first-class method in the 🤗 PEFT library: ShadowPEFT has a fundamentally different adapter geometry with LoRA, but it shares the same get_peft_model entry point as LoRA, the same adapter save/load path, and is easy to work with. This post starts with a brief PEFT recap, explains what ShadowPEFT changes conceptually, walks through the library integration, and presents head-to-head comparisons with LoRA and DoRA. Parameter-efficien
发布时间：—
抓取时间：2026-09-15 16:07
来源机构：Hugging Face