Alternatives and similar repositories for annotated-s4

Users that are interested in annotated-s4 are comparing it to the libraries listed below

• lindermanlab / S5
  ☆312Updated 11 months ago
• srush / annotated-mamba
  Annotated version of the Mamba paper
  ☆492Updated last year
• marin-community / levanter
  Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax
  ☆687Updated last month
• google-research / long-range-arena
  Long Range Arena for Benchmarking Efficient Transformers
  ☆771Updated 2 years ago
• google / flaxformer
  ☆364Updated last year
• HazyResearch / hippo-code
  ☆191Updated last year
• google-deepmind / nanodo
  ☆286Updated last year
• proger / accelerated-scan
  Accelerated First Order Parallel Associative Scan
  ☆193Updated this week
• kach / gradient-descent-the-ultimate-optimizer
  Code for our NeurIPS 2022 paper
  ☆370Updated 2 years ago
• google-research / meliad
  ☆259Updated 6 months ago
• facebookresearch / optimizers
  For optimization algorithm research and development.
  ☆553Updated this week
• HazyResearch / H3
  Language Modeling with the H3 State Space Model
  ☆521Updated 2 years ago
• facebookresearch / torchdim
  Named tensors with first-class dimensions for PyTorch
  ☆332Updated 2 years ago
• microsoft / mup
  maximal update parametrization (µP)
  ☆1,640Updated last year
• google-deepmind / neural_networks_chomsky_hierarchy
  Neural Networks and the Chomsky Hierarchy
  ☆212Updated last year
• ctlllll / SGConv
  ☆164Updated 2 years ago
• lucidrains / st-moe-pytorch
  Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch
  ☆374Updated last year
• ayaka14732 / jax-smi
  JAX Synergistic Memory Inspector
  ☆183Updated last year
• PeaBrane / mamba-tiny
  Simple, minimal implementation of the Mamba SSM in one pytorch file. Using logcumsumexp (Heisen sequence).
  ☆128Updated last year
• facebookresearch / mega
  Sequence modeling with Mega.
  ☆302Updated 2 years ago
• KellerJordan / cifar10-airbench
  CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
  ☆335Updated last month
• google-research / jaxpruner
  ☆234Updated 10 months ago
• srush / Transformer-Puzzles
  Puzzles for exploring transformers
  ☆380Updated 2 years ago
• google / learned_optimization
  ☆790Updated last month
• mlcommons / algorithmic-efficiency
  MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…
  ☆404Updated last week
• nikhilvyas / SOAP
  ☆230Updated last year
• loeweX / Forward-Forward
  Reimplementation of Geoffrey Hinton's Forward-Forward Algorithm
  ☆159Updated 2 years ago
• lucidrains / local-attention
  An implementation of local windowed attention for language modeling
  ☆491Updated 5 months ago
• state-spaces / s4
  Structured state space sequence models
  ☆2,801Updated last year
• srush / Autodiff-Puzzles
  ☆460Updated last year