rajveer43/titan_transformer
Unofficial implementation of titans transformer
This project offers advanced memory management for deep learning models, allowing them to process very long sequences of information more effectively. It takes in raw data from tasks like language modeling, time-series forecasting, or reasoning, and outputs models that can predict or understand these complex sequences with superior performance. This is for machine learning researchers and practitioners who build and train large language models or similar sequential data processors.
No commits in the last 6 months.
Use this if you need to train deep learning models that handle extensive historical context and struggle with memory limitations or maintaining long-term dependencies.
Not ideal if your deep learning tasks only involve short, independent data sequences or if you are not working with advanced neural network architectures.
Stars
8
Forks
1
Language
Jupyter Notebook
License
—
Category
Last pushed
Feb 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/rajveer43/titan_transformer"
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