Alternatives and similar repositories for SUT:

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

• bhoov / energy-transformer-jax
  The Energy Transformer block, in JAX
  ☆56Updated last year
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆44Updated last year
• bergen / EdgeTransformer
  ☆22Updated 3 years ago
• shawntan / stickbreaking-attention
  Stick-breaking attention
  ☆44Updated last month
• AndyShih12 / LongHorizonTemperatureScaling
  PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023
  ☆20Updated last year
• opallab / positional_attention
  Source code for the paper "Positional Attention: Out-of-Distribution Generalization and Expressivity for Neural Algorithmic Reasoning"
  ☆14Updated last month
• renll / SeqBoat
  [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling
  ☆35Updated last year
• shikaiqiu / compute-better-spent
  ☆52Updated 5 months ago
• IdoAmos / not-from-scratch
  ☆28Updated 4 months ago
• Blackzxy / LoGAH
  ☆21Updated 5 months ago
• RobertCsordas / moe
  Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"
  ☆36Updated last year
• jopetty / word-problem
  Experiments on the impact of depth in transformers and SSMs.
  ☆23Updated 3 months ago
• dangxingyu / rnn-icrag
  Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"
  ☆25Updated 10 months ago
• Doraemonzzz / xmixers
  Xmixers: A collection of SOTA efficient token/channel mixers
  ☆11Updated 3 months ago
• sjelassi / transformers_ssm_copy
  ☆30Updated last year
• sustcsonglin / mamba-triton
  ☆47Updated last year
• sustcsonglin / gated_linear_attention_layer
  ☆33Updated last year
• smonsays / hypernetwork-attention
  Official code for the paper "Attention as a Hypernetwork"
  ☆24Updated 8 months ago
• AndPotap / einsum-search
  ☆30Updated 4 months ago
• ablghtianyi / ICL_Modular_Arithmetic
  ☆18Updated 4 months ago
• google-deepmind / spectral_ssm
  ☆31Updated 10 months ago
• berlino / seq_icl
  ☆51Updated 9 months ago
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆58Updated last year
• lucidrains / pause-transformer
  Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…
  ☆53Updated last year
• johanwind / wind_rwkv
  ☆13Updated this week
• wzq016 / PINE
  Offcial Repo of Paper "Eliminating Position Bias of Language Models: A Mechanistic Approach""
  ☆11Updated 6 months ago
• janphilippfranken / sami
  Self-Supervised Alignment with Mutual Information
  ☆15Updated 9 months ago
• HKUNLP / diffusion-vs-ar
  [ICLR 2025] Code for the paper "Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning"
  ☆34Updated 2 weeks ago
• recursal / GoldFinch-paper
  GoldFinch and other hybrid transformer components
  ☆44Updated 7 months ago