Alternatives and similar repositories for minSAE

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

• thinking-machines-lab / manifolds
  Supporting code for the blog post on modular manifolds.
  ☆101Updated last month
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆83Updated 11 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
• cloneofsimo / scaling-guide
  WIP
  ☆93Updated last year
• ethansmith2000 / TransformerExperiments
  ☆19Updated 5 months ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆171Updated 4 months ago
• apple / ml-ademamix
  ☆68Updated 11 months ago
• fal-ai-community / nano-mdm
  Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun
  ☆57Updated 8 months ago
• fal-ai / diffusion-speedrun
  Focused on fast experimentation and simplicity
  ☆75Updated 10 months ago
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆132Updated last year
• cloneofsimo / min-fsdp
  ☆91Updated last year
• fal-ai-community / NativeSparseAttention
  research impl of Native Sparse Attention (2502.11089)
  ☆63Updated 8 months ago
• LIONS-EPFL / scion
  ☆47Updated 3 weeks ago
• test-time-training / ttt-tk
  ☆41Updated last week
• berlino / seq_icl
  ☆53Updated last year
• Laz4rz / mup
  Minimal (truly) muP implementation, consistent with TP4 and TP5 papers notation
  ☆14Updated 5 months ago
• HomebrewML / HeavyBall
  Efficient optimizers
  ☆276Updated 3 weeks ago
• nikhilvyas / SOAP
  ☆221Updated 11 months ago
• martin-marek / batch-size
  📄Small Batch Size Training for Language Models
  ☆63Updated last month
• main-horse / hnet-old
  H-Net Dynamic Hierarchical Architecture
  ☆80Updated 2 months ago
• cloneofsimo / karras-power-ema-tutorial
  ☆53Updated last year
• proger / accelerated-scan
  Accelerated First Order Parallel Associative Scan
  ☆189Updated last year
• huyphan168 / PEER
  Mixture of A Million Experts
  ☆49Updated last year
• JesseFarebro / flax-mup
  Maximal Update Parametrization (μP) with Flax & Optax.
  ☆16Updated last year
• cloneofsimo / zeroshampoo
  ☆34Updated last year
• tml-epfl / why-weight-decay
  Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]
  ☆68Updated last year
• brianfitzgerald / jax-mmdit
  Implementation of Diffusion Transformers and Rectified Flow in Jax
  ☆26Updated last year
• JonasGeiping / linear_cross_entropy_loss
  A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.
  ☆70Updated last year
• nikhilvyas / SOAP_MUON
  Combining SOAP and MUON
  ☆16Updated 9 months ago
• samsja / muon_fsdp_2
  Muon fsdp 2
  ☆44Updated 3 months ago