ischlag / fast-weight-transformersLinks
Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.
☆105Updated 4 years ago
Alternatives and similar repositories for fast-weight-transformers
Users that are interested in fast-weight-transformers are comparing it to the libraries listed below
Sorting:
- Official repository for the paper "Going Beyond Linear Transformers with Recurrent Fast Weight Programmers" (NeurIPS 2021)☆49Updated 2 weeks ago
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆100Updated 2 years ago
- The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We s…☆67Updated 2 years ago
- Implementation of Feedback Transformer in Pytorch☆107Updated 4 years ago
- Implementation of Memformer, a Memory-augmented Transformer, in Pytorch☆118Updated 4 years ago
- Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper☆81Updated 3 years ago
- An implementation of (Induced) Set Attention Block, from the Set Transformers paper☆59Updated 2 years ago
- Fast Discounted Cumulative Sums in PyTorch☆96Updated 3 years ago
- CUDA kernels for generalized matrix-multiplication in PyTorch☆84Updated 3 years ago
- Code for the paper PermuteFormer☆42Updated 3 years ago
- Pytorch implementation of Compressive Transformers, from Deepmind☆160Updated 3 years ago
- Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch☆119Updated 3 years ago
- GPT, but made only out of MLPs☆89Updated 4 years ago
- An implementation of Transformer with Expire-Span, a circuit for learning which memories to retain☆34Updated 4 years ago
- Drop-in replacement for any ResNet with a significantly reduced memory footprint and better representation capabilities☆209Updated last year
- An implementation of 2021 paper by Geoffrey Hinton: "How to represent part-whole hierarchies in a neural network" in Pytorch.☆58Updated 4 years ago
- [NeurIPS 2020] Official Implementation: "SMYRF: Efficient Attention using Asymmetric Clustering".☆50Updated last year
- Axial Positional Embedding for Pytorch☆81Updated 4 months ago
- [ICML 2020] code for "PowerNorm: Rethinking Batch Normalization in Transformers" https://arxiv.org/abs/2003.07845☆120Updated 4 years ago
- A custom PyTorch layer that is capable of implementing extremely wide and sparse linear layers efficiently☆50Updated last year
- Structured matrices for compressing neural networks☆67Updated last year
- Sequence Modeling with Structured State Spaces☆64Updated 2 years ago
- Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method (NeurIPS 2021)☆61Updated 3 years ago
- Code to reproduce the results for Compositional Attention☆60Updated 2 years ago
- An attempt at the implementation of Glom, Geoffrey Hinton's new idea that integrates concepts from neural fields, top-down-bottom-up proc…☆194Updated 4 years ago
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆225Updated 3 years ago
- The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".☆33Updated 2 weeks ago
- Easy-to-use AdaHessian optimizer (PyTorch)☆79Updated 4 years ago
- Code for Multi-Head Attention: Collaborate Instead of Concatenate☆152Updated 2 years ago
- [ICML 2021 Oral] We show pure attention suffers rank collapse, and how different mechanisms combat it.☆165Updated 4 years ago