Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
13.4
TFLOPS
24
1
33
Lucas Silva
PRO
YuLexuan30
Follow
webxos's profile picture
rooox's profile picture
Chucho-1012's profile picture
8 followers
·
9 following
AI & ML interests
None yet
Recent Activity
liked
a Space
about 14 hours ago
multimodalart/nano-banana
liked
a Space
8 days ago
cbensimon/FLUX.2-dev-turbo
reacted
to
SeanLee97
's
post
with 🚀
16 days ago
Our lab recently released a paper where we introduce ShadowPEFT, a new Parameter-Efficient Fine-Tuning (PEFT) paradigm tailored for edge computing scenarios. Unlike traditional approaches such as LoRA and its variants, which inject trainable parameters directly into the weights of Transformer, requiring tight coupling with the backbone. ShadowPEFT instead enhances the frozen large base model by adding a lightweight, centralized, pretrainable, and detachable Shadow network. This shadow network operates in parallel with the base model, delivering learned corrections to each decoder layer. Because the shadow module is architecturally decoupled from the backbone, it can be independently trained, stored, and deployed, benefiting edge computing scenarios and edge-cloud collaboration computing. - HF Paper: https://huggingface.co/papers/2604.19254 - GitHub: https://github.com/ShadowLLM/shadow-peft - HF Collection: https://huggingface.co/collections/shadow-llm/shadow-peft-models
View all activity
Organizations
YuLexuan30
's Spaces
1
Sort: Recently updated
Sleeping
Agents
ForgeCaptions
⚡
ForgeCaptions is a flexible captioning and dataset-prep tool