Alternatives and similar repositories for minSAE:

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

• cloneofsimo / ezmup
  Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam
  ☆71Updated 4 months ago
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆68Updated last week
• ethansmith2000 / TransformerExperiments
  ☆18Updated 2 months ago
• cloneofsimo / min-fsdp
  ☆74Updated 5 months ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆85Updated 3 weeks ago
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆113Updated 8 months ago
• cloneofsimo / scaling-guide
  WIP
  ☆89Updated 4 months ago
• cloneofsimo / zeroshampoo
  ☆31Updated 3 months ago
• evanatyourservice / kron_torch
  An implementation of PSGD Kron second-order optimizer for PyTorch
  ☆19Updated 2 weeks ago
• cloneofsimo / efae
  ☆21Updated 5 months ago
• dvruette / barrel-rec-pytorch
  ☆53Updated 10 months ago
• apple / ml-ademamix
  ☆50Updated last month
• shikaiqiu / compute-better-spent
  ☆48Updated 2 months ago
• cloneofsimo / repa-rf
  ☆31Updated last month
• young-geng / mintext
  Minimal but scalable implementation of large language models in JAX
  ☆27Updated last month
• nikhilvyas / SOAP
  ☆138Updated 2 weeks ago
• cloneofsimo / karras-power-ema-tutorial
  ☆51Updated 11 months ago
• thecharlieblake / lovely-llama
  An implementation of the Llama architecture, to instruct and delight
  ☆21Updated 4 months ago
• cloneofsimo / insightful-nn-papers
  These papers will provide unique insightful concepts that will broaden your perspective on neural networks and deep learning
  ☆46Updated last year
• joey00072 / ohara
  Collection of autoregressive model implementation
  ☆67Updated 3 weeks ago
• lucaslingle / mu_transformer
  Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.
  ☆30Updated this week
• lucidrains / grokfast-pytorch
  Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"
  ☆89Updated last week
• berlino / seq_icl
  ☆51Updated 6 months ago
• cloneofsimo / min-max-in-dit
  ☆26Updated 7 months ago
• ClashLuke / HeavyBall
  Efficient optimizers
  ☆126Updated this week
• RobertCsordas / moeut
  ☆64Updated 3 months ago
• epfml / schedules-and-scaling
  ☆60Updated last month
• NVlabs / GatedDeltaNet
  Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule
  ☆45Updated this week
• radarFudan / mamba-minimal-jax
  ☆29Updated 3 weeks ago
• yixiaoer / tpu-training-example
  ☆13Updated 5 months ago