HKUNLP/efficient-attention

[EVA ICLR'23; LARA ICML'22] Efficient attention mechanisms via control variates, random features, and importance sampling

32
/ 100
Emerging

This project provides advanced attention mechanisms (LARA and EVA) to make image classification and machine translation models run faster and more efficiently. It takes in standard image datasets like ImageNet or text data for translation tasks, and outputs more optimized models. This is for machine learning engineers and researchers who are building and training advanced AI models for vision and language applications.

No commits in the last 6 months.

Use this if you are a machine learning engineer working with vision transformers or language models and need to improve the efficiency and speed of your attention mechanisms during model training and inference.

Not ideal if you are an end-user without a strong background in deep learning model development or if you need a plug-and-play solution for basic image or text processing without delving into model architecture.

image-classification machine-translation language-modeling deep-learning-optimization vision-transformers
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

87

Forks

4

Language

Python

License

Apache-2.0

Last pushed

Mar 07, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/HKUNLP/efficient-attention"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.