Alternatives and similar repositories for nanoTransNormer

Users that are interested in nanoTransNormer are comparing it to the libraries listed below

• glassroom / heinsen_attention
  Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)
  ☆24Updated 11 months ago
• johanwind / wind_rwkv
  ☆17Updated last month
• dangxingyu / rnn-icrag
  Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"
  ☆27Updated last year
• sustcsonglin / gated_linear_attention_layer
  ☆31Updated last year
• jopetty / word-problem
  Experiments on the impact of depth in transformers and SSMs.
  ☆30Updated 6 months ago
• maximzubkov / fft-scan
  Efficient PScan implementation in PyTorch
  ☆16Updated last year
• yikangshen / megablocks
  ☆20Updated last year
• bdusell / stack-attention
  Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"
  ☆17Updated last year
• emalach / LinearLM
  Code for the paper: https://arxiv.org/pdf/2309.06979.pdf
  ☆19Updated 10 months ago
• EleutherAI / rnngineering
  Engineering the state of RNN language models (Mamba, RWKV, etc.)
  ☆32Updated last year
• Doraemonzzz / xmixers
  Xmixers: A collection of SOTA efficient token/channel mixers
  ☆11Updated 6 months ago
• jenni-ai / T2FW
  Fine-Tuning Pre-trained Transformers into Decaying Fast Weights
  ☆19Updated 2 years ago
• acosharma / elita-transformer
  Official Repository for Efficient Linear-Time Attention Transformers.
  ☆18Updated last year
• sustcsonglin / mamba-triton
  ☆46Updated last year
• sjelassi / transformers_ssm_copy
  ☆31Updated 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 2 months ago
• smonsays / hypernetwork-attention
  Official code for the paper "Attention as a Hypernetwork"
  ☆36Updated 11 months ago
• ethansmith2000 / TransformerExperiments
  ☆19Updated 2 weeks ago
• renll / SeqBoat
  [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling
  ☆36Updated last year
• RobertCsordas / moe
  Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"
  ☆37Updated last year
• Doraemonzzz / hgru2-pytorch
  ☆23Updated 8 months ago
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆58Updated last year
• RobertCsordas / moe_layer
  sigma-MoE layer
  ☆18Updated last year
• Ryu1845 / hyena-jax
  Implementation of Hyena Hierarchy in JAX
  ☆10Updated 2 years ago
• recursal / GoldFinch-paper
  GoldFinch and other hybrid transformer components
  ☆45Updated 10 months ago
• shawntan / SUT
  Repository for Sparse Universal Transformers
  ☆18Updated last year
• nanowell / Q-Sparse-LLM
  My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated
  ☆32Updated 9 months ago
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆43Updated 8 months ago
• jungokasai / T2R
  ☆14Updated 2 years ago
• HazyResearch / prefix-linear-attention
  ☆54Updated 10 months ago