Alternatives and similar repositories for state-tracking

Users that are interested in state-tracking are comparing it to the libraries listed below

• GindaChen / FlexFlashAttention3
  FlexAttention w/ FlashAttention3 Support
  ☆26Updated 9 months ago
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆60Updated last year
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆44Updated 9 months ago
• kazuki-irie / kv-memory-brain
  Official Code Repository for the paper "Key-value memory in the brain"
  ☆27Updated 4 months ago
• Doraemonzzz / Awesome-Triton-Resources
  Awesome Triton Resources
  ☆32Updated 2 months ago
• Ryu1845 / hyena-jax
  Implementation of Hyena Hierarchy in JAX
  ☆10Updated 2 years ago
• dangxingyu / rnn-icrag
  Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"
  ☆27Updated last year
• sustcsonglin / mamba-triton
  ☆48Updated last year
• proger / nanokitchen
  Parallel Associative Scan for Language Models
  ☆18Updated last year
• jopetty / word-problem
  Experiments on the impact of depth in transformers and SSMs.
  ☆32Updated 8 months ago
• sustcsonglin / gated_linear_attention_layer
  ☆32Updated last year
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆48Updated last year
• yikangshen / megablocks
  ☆20Updated last year
• EleutherAI / rnngineering
  Engineering the state of RNN language models (Mamba, RWKV, etc.)
  ☆32Updated last year
• hazan-lab / flash-stu
  PyTorch implementation of the Flash Spectral Transform Unit.
  ☆17Updated 9 months ago
• emalach / LinearLM
  Code for the paper: https://arxiv.org/pdf/2309.06979.pdf
  ☆19Updated 11 months ago
• srush / tangent
  Source-to-Source Debuggable Derivatives in Pure Python
  ☆15Updated last year
• google-deepmind / spectral_ssm
  ☆32Updated last year
• glassroom / heinsen_attention
  Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)
  ☆24Updated last year
• automl / unlocking_state_tracking
  Expanding linear RNN state-transition matrix eigenvalues to include negatives improves state-tracking tasks and language modeling without…
  ☆15Updated 4 months ago
• nikhilvyas / SOAP_MUON
  Combining SOAP and MUON
  ☆16Updated 5 months ago
• srush / mamba-primer
  ☆37Updated last year
• shawntan / stickbreaking-attention
  Stick-breaking attention
  ☆58Updated 2 weeks ago
• sjelassi / transformers_ssm_copy
  ☆32Updated last year
• bdusell / stack-attention
  Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"
  ☆17Updated last year
• edwardmilsom / function-space-learning-rates-paper
  Code for the paper "Function-Space Learning Rates"
  ☆20Updated last month
• smonsays / hypernetwork-attention
  Official code for the paper "Attention as a Hypernetwork"
  ☆40Updated last year
• Doraemonzzz / hgru2-pytorch
  ☆23Updated 9 months ago
• AndPotap / einsum-search
  ☆32Updated 9 months ago
• EleutherAI / mdl
  Minimum Description Length probing for neural network representations
  ☆18Updated 5 months ago