Alternatives and similar repositories for fast-weight-transformers

Users that are interested in fast-weight-transformers are comparing it to the libraries listed below

• RobertCsordas / transformer_generalization
  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
• IDSIA / recurrent-fwp
  Official repository for the paper "Going Beyond Linear Transformers with Recurrent Fast Weight Programmers" (NeurIPS 2021)
  ☆50Updated 5 months ago
• toshas / torch-discounted-cumsum
  Fast Discounted Cumulative Sums in PyTorch
  ☆96Updated 4 years ago
• giannisdaras / smyrf
  [NeurIPS 2020] Official Implementation: "SMYRF: Efficient Attention using Asymmetric Clustering".
  ☆50Updated 2 years ago
• lucidrains / ponder-transformer
  Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper
  ☆81Updated 4 years ago
• mcbal / deep-implicit-attention
  Implementation of deep implicit attention in PyTorch
  ☆65Updated 4 years ago
• lucidrains / gated-state-spaces-pytorch
  Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch
  ☆101Updated 2 years ago
• lucidrains / learning-to-expire-pytorch
  An implementation of Transformer with Expire-Span, a circuit for learning which memories to retain
  ☆34Updated 5 years ago
• lucidrains / feedback-transformer-pytorch
  Implementation of Feedback Transformer in Pytorch
  ☆108Updated 4 years ago
• RedRyan111 / GLOM
  An implementation of 2021 paper by Geoffrey Hinton: "How to represent part-whole hierarchies in a neural network" in Pytorch.
  ☆57Updated 4 years ago
• lucidrains / product-key-memory
  Standalone Product Key Memory module in Pytorch - for augmenting Transformer models
  ☆86Updated 2 weeks ago
• epfml / collaborative-attention
  Code for Multi-Head Attention: Collaborate Instead of Concatenate
  ☆151Updated 2 years ago
• lucidrains / compressive-transformer-pytorch
  Pytorch implementation of Compressive Transformers, from Deepmind
  ☆162Updated 4 years ago
• ag1988 / dss
  Sequence Modeling with Structured State Spaces
  ☆66Updated 3 years ago
• lucidrains / ESBN-pytorch
  Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch
  ☆25Updated 4 years ago
• Noahs-ARK / RFA
  ☆33Updated 4 years ago
• harvardnlp / genbmm
  CUDA kernels for generalized matrix-multiplication in PyTorch
  ☆85Updated 4 years ago
• sIncerass / powernorm
  [ICML 2020] code for "PowerNorm: Rethinking Batch Normalization in Transformers" https://arxiv.org/abs/2003.07845
  ☆120Updated 4 years ago
• HazyResearch / structured-nets
  Structured matrices for compressing neural networks
  ☆67Updated 2 years ago
• sarthmit / Compositional-Attention
  Code to reproduce the results for Compositional Attention
  ☆59Updated 3 years ago
• lucidrains / glom-pytorch
  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
• cpcp1998 / PermuteFormer
  Code for the paper PermuteFormer
  ☆42Updated 4 years ago
• lucidrains / isab-pytorch
  An implementation of (Induced) Set Attention Block, from the Set Transformers paper
  ☆65Updated 2 years ago
• lucidrains / g-mlp-gpt
  GPT, but made only out of MLPs
  ☆89Updated 4 years ago
• lucidrains / HTM-pytorch
  Implementation of Hierarchical Transformer Memory (HTM) for Pytorch
  ☆76Updated 4 years ago
• ssnl / PyTorch-Reparam-Module
  Reparameterize your PyTorch modules
  ☆71Updated 4 years ago
• hyeon95y / SparseLinear
  A custom PyTorch layer that is capable of implementing extremely wide and sparse linear layers efficiently
  ☆51Updated last year
• wouterkool / estimating-gradients-without-replacement
  Estimating Gradients for Discrete Random Variables by Sampling without Replacement
  ☆40Updated 5 years ago
• twistedcubic / attention-rank-collapse
  [ICML 2021 Oral] We show pure attention suffers rank collapse, and how different mechanisms combat it.
  ☆167Updated 4 years ago
• facebookresearch / transformer-sequential
  Trains Transformer model variants. Data isn't shuffled between batches.
  ☆143Updated 3 years ago