SakanaAI/evo-memory

Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.

34
/ 100
Emerging

This project offers a method to train and evaluate advanced neural network memory systems, specifically for transformer models. It takes pre-existing transformer models and long-sequence datasets as input to produce optimized memory components. AI researchers and machine learning engineers focusing on improving the long-term memory capabilities of large language models would find this useful.

352 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer aiming to develop or enhance transformer-based AI models with more effective and universally applicable memory for processing very long texts.

Not ideal if you are looking for an out-of-the-box solution for applying AI models to business problems, rather than developing the underlying AI architecture itself.

AI model development natural language processing research transformer architecture large language models deep learning memory systems
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

352

Forks

38

Language

Python

License

Last pushed

Oct 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/SakanaAI/evo-memory"

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