Alternatives and similar repositories for minSAE

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

• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆84Updated last year
• cloneofsimo / scaling-guide
  WIP
  ☆93Updated last year
• fal-ai-community / nano-mdm
  Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun
  ☆56Updated 10 months ago
• cloneofsimo / ezmup
  Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam
  ☆85Updated last year
• thinking-machines-lab / manifolds
  Supporting code for the blog post on modular manifolds.
  ☆115Updated 4 months ago
• fal-ai-community / NativeSparseAttention
  research impl of Native Sparse Attention (2502.11089)
  ☆63Updated 11 months ago
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆132Updated last year
• apple / ml-ademamix
  ☆70Updated last year
• fal-ai / diffusion-speedrun
  Focused on fast experimentation and simplicity
  ☆80Updated last year
• ethansmith2000 / TransformerExperiments
  ☆19Updated 2 months ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆186Updated 2 weeks ago
• cloneofsimo / min-fsdp
  ☆92Updated last year
• test-time-training / ttt-tk
  ☆44Updated 3 months ago
• LIONS-EPFL / scion
  ☆53Updated last month
• cloneofsimo / karras-power-ema-tutorial
  ☆53Updated 2 years ago
• berlino / seq_icl
  ☆53Updated last year
• cloneofsimo / zeroshampoo
  ☆34Updated last year
• lindermanlab / elk
  Scalable and Stable Parallelization of Nonlinear RNNS
  ☆28Updated 3 months ago
• main-horse / hnet-old
  H-Net Dynamic Hierarchical Architecture
  ☆81Updated 4 months ago
• opooladz / Preconditioned-Stochastic-Gradient-Descent
  A repo based on XiLin Li's PSGD repo that extends some of the experiments.
  ☆14Updated last year
• zaydzuhri / softpick-attention
  Landing repository for the paper "Softpick: No Attention Sink, No Massive Activations with Rectified Softmax"
  ☆86Updated 4 months ago
• nikhilvyas / SOAP
  ☆246Updated last year
• dvruette / gidd
  Code accompanying the paper "Generalized Interpolating Discrete Diffusion"
  ☆113Updated 7 months ago
• JesseFarebro / flax-mup
  Maximal Update Parametrization (μP) with Flax & Optax.
  ☆16Updated 2 years ago
• HomebrewML / HeavyBall
  Efficient optimizers
  ☆281Updated last month
• young-geng / mintext
  Minimal but scalable implementation of large language models in JAX
  ☆35Updated 2 months ago
• dayal-kalra / low-memory-adam
  ☆14Updated 11 months ago
• lucidrains / taylor-series-linear-attention
  Explorations into the recently proposed Taylor Series Linear Attention
  ☆100Updated last year
• proger / accelerated-scan
  Accelerated First Order Parallel Associative Scan
  ☆196Updated last month
• apple / ml-act
  ☆58Updated last year