ziplab/ZipLLM

Stars
1
Language
Created 4 months ago
Updated 4 months ago

ziplab/ZipLLM

ziplab

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

SN-Net

[CVPR 2023 Highlight] This is the official implementation of "Stitchable Neural Networks".

LITv2

[NeurIPS 2022 Spotlight] This is the official PyTorch implementation of "Fast Vision Transformers with HiLo Attention"

Mesa

This is the official PyTorch implementation for "Mesa: A Memory-saving Training Framework for Transformers".

SPViT

[TPAMI 2024] This is the official repository for our paper: ''Pruning Self-attentions into Convolutional Layers in Single Path''.

LIT

[AAAI 2022] This is the official PyTorch implementation of "Less is More: Pay Less Attention in Vision Transformers"

PTQD

The official implementation of PTQD: Accurate Post-Training Quantization for Diffusion Models

Jupyter Notebook

QTool

Collections of model quantization algorithms. Any issues, please contact Peng Chen ([email protected])

EcoFormer

[NeurIPS 2022 Spotlight] This is the official PyTorch implementation of "EcoFormer: Energy-Saving Attention with Linear Complexity"

SPT

[ICCV 2023 oral] This is the official repository for our paper: ''Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning''.

FASeg

[CVPR 2023] This is the official PyTorch implementation for "Dynamic Focus-aware Positional Queries for Semantic Segmentation".

SAQ

This is the official PyTorch implementation for "Sharpness-aware Quantization for Deep Neural Networks".

LongVLM

HVT

[ICCV 2021] Official implementation of "Scalable Vision Transformers with Hierarchical Pooling"

MPVSS

SN-Netv2

[ECCV 2024] This is the official implementation of "Stitched ViTs are Flexible Vision Backbones".

QLLM

[ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models"

efficient-stable-diffusion

Stitched_LLaMA

[CVPR 2024] A framework to fine-tune LLaMAs on instruction-following task and get many Stitched LLaMAs with customized number of parameters, e.g., Stitched LLaMA 8B, 9B, and 10B...

STPT