gmlwns2000/sttabt
[ICLR2023] Official code of Sparse Token Transformer with Attention Back-Tracking
This project offers a way for machine learning engineers to make their Transformer-based AI models run more efficiently on devices with limited memory and processing power, like mobile phones or edge devices. It takes an existing Transformer model and optimizes it, resulting in a model that uses less memory and computes faster while maintaining strong performance on tasks like image classification or natural language processing. The end-users are machine learning engineers deploying AI models in resource-constrained environments.
No commits in the last 6 months.
Use this if you are a machine learning engineer working with Transformer models and need to reduce their computational and memory footprint for deployment on mobile or edge devices without significantly sacrificing accuracy.
Not ideal if you are working with non-Transformer neural network architectures or if your deployment environment has ample computational resources and memory.
Stars
8
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/gmlwns2000/sttabt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/x-transformers
A concise but complete full-attention transformer with a set of promising experimental features...
kanishkamisra/minicons
Utility for behavioral and representational analyses of Language Models
lucidrains/simple-hierarchical-transformer
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
Nicolepcx/Transformers-in-Action
This is the corresponding code for the book Transformers in Action