SakanaAI/evo-memory
Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.
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.
Stars
352
Forks
38
Language
Python
License
—
Category
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.
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