ironjr / grokfastLinks
Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"
☆564Updated last year
Alternatives and similar repositories for grokfast
Users that are interested in grokfast are comparing it to the libraries listed below
Sorting:
- Efficient optimizers☆275Updated last week
- The AdEMAMix Optimizer: Better, Faster, Older.☆186Updated last year
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆292Updated 5 months ago
- Annotated version of the Mamba paper☆489Updated last year
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆324Updated 4 months ago
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆927Updated this week
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆351Updated last year
- A repository for log-time feedforward networks☆222Updated last year
- 🧱 Modula software package☆303Updated 3 months ago
- Official JAX implementation of xLSTM including fast and efficient training and inference code. 7B model available at https://huggingface.…☆104Updated 10 months ago
- Open weights language model from Google DeepMind, based on Griffin.☆652Updated 5 months ago
- Getting crystal-like representations with harmonic loss☆192Updated 7 months ago
- For optimization algorithm research and development.☆544Updated this week
- Simple, minimal implementation of the Mamba SSM in one pytorch file. Using logcumsumexp (Heisen sequence).☆126Updated last year
- Training small GPT-2 style models using Kolmogorov-Arnold networks.☆121Updated last year
- ☆223Updated 11 months ago
- ☆105Updated 3 months ago
- Reverse Engineering the Abstraction and Reasoning Corpus☆312Updated 8 months ago
- The boundary of neural network trainability is fractal☆220Updated last year
- Our solution for the arc challenge 2024☆185Updated 5 months ago
- ☆310Updated last year
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆561Updated 10 months ago
- Implementation of Diffusion Transformer (DiT) in JAX☆296Updated last year
- ☆285Updated last year
- Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.☆281Updated last year
- DeMo: Decoupled Momentum Optimization☆197Updated 11 months ago
- The repository for the code of the UltraFastBERT paper☆519Updated last year
- The history files when recording human interaction while solving ARC tasks☆118Updated this week
- Normalized Transformer (nGPT)☆192Updated last year
- Pretraining and inference code for a large-scale depth-recurrent language model☆847Updated last month