Alternatives and similar repositories for grokfast

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

• nanowell / AdEMAMix-Optimizer-Pytorch
  The AdEMAMix Optimizer: Better, Faster, Older.
  ☆184Updated 10 months ago
• HomebrewML / HeavyBall
  Efficient optimizers
  ☆252Updated last week
• lucidrains / nGPT-pytorch
  Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI
  ☆289Updated 2 months ago
• srush / annotated-mamba
  Annotated version of the Mamba paper
  ☆487Updated last year
• microsoft / Samba
  [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
  ☆901Updated 3 months ago
• NX-AI / xlstm-jax
  Official JAX implementation of xLSTM including fast and efficient training and inference code. 7B model available at https://huggingface.…
  ☆98Updated 6 months ago
• nikhilvyas / SOAP
  ☆206Updated 8 months ago
• kvfrans / jax-diffusion-transformer
  Implementation of Diffusion Transformer (DiT) in JAX
  ☆286Updated last year
• PeaBrane / mamba-tiny
  Simple, minimal implementation of the Mamba SSM in one pytorch file. Using logcumsumexp (Heisen sequence).
  ☆120Updated 9 months ago
• LucasPrietoAl / grokking-at-the-edge-of-numerical-stability
  ☆100Updated 2 weeks ago
• facebookresearch / optimizers
  For optimization algorithm research and development.
  ☆525Updated this week
• KellerJordan / cifar10-airbench
  CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
  ☆274Updated 3 weeks ago
• pbelcak / fastfeedforward
  A repository for log-time feedforward networks
  ☆222Updated last year
• KindXiaoming / grow-crystals
  Getting crystal-like representations with harmonic loss
  ☆192Updated 4 months ago
• google-deepmind / nanodo
  ☆275Updated last year
• NVIDIA / ngpt
  Normalized Transformer (nGPT)
  ☆185Updated 8 months ago
• google-deepmind / recurrentgemma
  Open weights language model from Google DeepMind, based on Griffin.
  ☆645Updated 2 months ago
• Sohl-Dickstein / fractal
  The boundary of neural network trainability is fractal
  ☆215Updated last year
• CG80499 / KAN-GPT-2
  Training small GPT-2 style models using Kolmogorov-Arnold networks.
  ☆121Updated last year
• modula-systems / modula
  🧱 Modula software package
  ☆216Updated last week
• HazyResearch / m2
  Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"
  ☆555Updated 7 months ago
• tysam-code / hlb-gpt
  Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…
  ☆349Updated last year
• pbelcak / UltraFastBERT
  The repository for the code of the UltraFastBERT paper
  ☆516Updated last year
• zyushun / Adam-mini
  Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793
  ☆431Updated 2 months ago
• bloc97 / DeMo
  DeMo: Decoupled Momentum Optimization
  ☆190Updated 8 months ago
• SakanaAI / evo-memory
  Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.
  ☆318Updated 9 months ago
• seal-rg / recurrent-pretraining
  Pretraining and inference code for a large-scale depth-recurrent language model
  ☆808Updated 2 weeks ago
• apple / ml-sigma-reparam
  ☆304Updated last year
• KellerJordan / Muon
  Muon is an optimizer for hidden layers in neural networks
  ☆1,390Updated 3 weeks ago
• erfanzar / EasyDeL
  Accelerate, Optimize performance with streamlined training and serving options with JAX.
  ☆293Updated this week