• Stars
    star
    88
  • Rank 375,370 (Top 8 %)
  • Language
    Python
  • License
    Apache License 2.0
  • Created over 3 years ago
  • Updated over 2 years ago

Reviews

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

Repository Details

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

More Repositories

1

SN-Net

[CVPR 2023 Highlight] This is the official implementation of "Stitchable Neural Networks".
Python
238
star
2

LITv2

[NeurIPS 2022 Spotlight] This is the official PyTorch implementation of "Fast Vision Transformers with HiLo Attention"
Python
233
star
3

Mesa

This is the official PyTorch implementation for "Mesa: A Memory-saving Training Framework for Transformers".
Python
119
star
4

SPViT

[TPAMI 2024] This is the official repository for our paper: ''Pruning Self-attentions into Convolutional Layers in Single Path''.
Python
104
star
5

PTQD

The official implementation of PTQD: Accurate Post-Training Quantization for Diffusion Models
Jupyter Notebook
85
star
6

QTool

Collections of model quantization algorithms. Any issues, please contact Peng Chen ([email protected])
Python
68
star
7

EcoFormer

[NeurIPS 2022 Spotlight] This is the official PyTorch implementation of "EcoFormer: Energy-Saving Attention with Linear Complexity"
Python
66
star
8

SPT

[ICCV 2023 oral] This is the official repository for our paper: ''Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning''.
Python
60
star
9

FASeg

[CVPR 2023] This is the official PyTorch implementation for "Dynamic Focus-aware Positional Queries for Semantic Segmentation".
Python
54
star
10

SAQ

This is the official PyTorch implementation for "Sharpness-aware Quantization for Deep Neural Networks".
Python
40
star
11

LongVLM

Python
38
star
12

HVT

[ICCV 2021] Official implementation of "Scalable Vision Transformers with Hierarchical Pooling"
Python
30
star
13

MPVSS

Python
25
star
14

SN-Netv2

[ECCV 2024] This is the official implementation of "Stitched ViTs are Flexible Vision Backbones".
Python
22
star
15

QLLM

[ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models"
Python
19
star
16

efficient-stable-diffusion

16
star
17

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...
8
star
18

STPT

3
star
19

ZipLLM

1
star