Building on HF
not-lain
Β·
AI & ML interests
custom AI models with HF integration, HuggingFace fellow π€
Recent Activity
reacted to SeanLee97's post with π 1 day 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
reacted to SeanLee97's post with π₯ 1 day 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
not-lain/finetuned_deepseek_ocr
Text Generation
β’ 3B β’ Updated β’ 2
β’ 1
not-lain/Quotes_Generator
Updated β’ 1
2B β’ Updated β’ 5
Robotics
β’ 2B β’ Updated β’ 4
β’ 1
2B β’ Updated β’ 4
Updated β’ 5
β’ 1
Mask Generation
β’ Updated not-lain/swarmformer-base
Updated β’ 5
not-lain/MAT-CelebA-HQ_512
Image-to-Image
β’ Updated β’ 2
Image-to-Image
β’ 0.2B β’ Updated β’ 65
Image Segmentation
β’ Updated β’ 6
β’ 1
Text-to-Speech
β’ Updated β’ 4
β’ 3
Updated β’ 1
Text Generation
β’ 0.1B β’ Updated β’ 1
Text Generation
β’ 0.1B β’ Updated β’ 1
Text Generation
β’ 0.1B β’ Updated β’ 1
Updated β’ 3
β’ 1
Updated β’ 5
Image Classification
β’ Updated β’ 4
not-lain/BiRefNet-massive
Updated β’ 5
β’ 1
Text Generation
β’ 1B β’ Updated β’ 5
not-lain/Depth-Anything-V2-Base
Depth Estimation
β’ Updated β’ 5