Alternatives and similar repositories for grokfast

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

• HomebrewML / HeavyBall
  Efficient optimizers
  ☆275Updated 2 weeks ago
• nanowell / AdEMAMix-Optimizer-Pytorch
  The AdEMAMix Optimizer: Better, Faster, Older.
  ☆186Updated last year
• KellerJordan / cifar10-airbench
  CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
  ☆320Updated 3 months ago
• KindXiaoming / grow-crystals
  Getting crystal-like representations with harmonic loss
  ☆192Updated 6 months ago
• srush / annotated-mamba
  Annotated version of the Mamba paper
  ☆490Updated last year
• lucidrains / nGPT-pytorch
  Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI
  ☆291Updated 4 months ago
• modula-systems / modula
  🧱 Modula software package
  ☆291Updated 2 months ago
• pbelcak / fastfeedforward
  A repository for log-time feedforward networks
  ☆222Updated last year
• microsoft / Samba
  [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
  ☆917Updated 6 months ago
• LucasPrietoAl / grokking-at-the-edge-of-numerical-stability
  ☆102Updated 3 months ago
• CG80499 / KAN-GPT-2
  Training small GPT-2 style models using Kolmogorov-Arnold networks.
  ☆121Updated last year
• nikhilvyas / SOAP
  ☆220Updated 10 months ago
• google-deepmind / recurrentgemma
  Open weights language model from Google DeepMind, based on Griffin.
  ☆653Updated 4 months ago
• Sohl-Dickstein / fractal
  The boundary of neural network trainability is fractal
  ☆217Updated last year
• neurallambda / neurallambda
  Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.
  ☆279Updated 11 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…
  ☆350Updated last year
• facebookresearch / optimizers
  For optimization algorithm research and development.
  ☆543Updated last week
• google-deepmind / nanodo
  ☆283Updated last year
• da-fr / arc-prize-2024
  Our solution for the arc challenge 2024
  ☆182Updated 4 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.…
  ☆104Updated 9 months ago
• zyushun / Adam-mini
  Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793
  ☆440Updated 5 months ago
• seal-rg / recurrent-pretraining
  Pretraining and inference code for a large-scale depth-recurrent language model
  ☆838Updated 2 weeks ago
• jerber / lang-jepa
  ☆124Updated 10 months ago
• gautierdag / bpeasy
  Fast bare-bones BPE for modern tokenizer training
  ☆167Updated 4 months ago
• HazyResearch / m2
  Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"
  ☆560Updated 10 months ago
• michaelhodel / re-arc
  Reverse Engineering the Abstraction and Reasoning Corpus
  ☆308Updated 8 months ago
• SakanaAI / evo-memory
  Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.
  ☆325Updated last year
• NVIDIA / ngpt
  Normalized Transformer (nGPT)
  ☆192Updated 11 months ago
• bloc97 / DeMo
  DeMo: Decoupled Momentum Optimization
  ☆194Updated 10 months ago
• iShohei220 / adopt
  Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"
  ☆426Updated 10 months ago