Implementation of the Legendre Memory Unit in PyTorch
OTHER License
Statistics for this project are still being loaded, please check back later.
Implementation of Memformer, a Memory-augmented Transformer, in Pytorch
Minimal, clean example of lstm neural network training in python, for learning purposes.
Pytorch implementation of Compressive Transformers, from Deepmind
Example of holographic reduced representations in Tensorflow
Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and ...
Implementation of Block Recurrent Transformer - Pytorch
Deep Learning Architecture Genealogy Project
Implementation of Hierarchical Transformer Memory (HTM) for Pytorch
MambaOut: Do We Really Need Mamba for Vision?
Re-implementation: Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
Make huge neural nets fit in memory
Official repository of the xLSTM.
Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch
Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attenti...
A variant of Transformer-XL where the memory is updated not with a queue, but with attention