ironjr / grokfastLinks
Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"
☆573Updated 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☆281Updated last month
- The AdEMAMix Optimizer: Better, Faster, Older.☆186Updated last year
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆293Updated 7 months ago
- Annotated version of the Mamba paper☆493Updated last year
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆344Updated 2 months ago
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆941Updated 2 months ago
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆562Updated last year
- Open weights language model from Google DeepMind, based on Griffin.☆659Updated 7 months ago
- Getting crystal-like representations with harmonic loss☆195Updated 9 months ago
- A repository for log-time feedforward networks☆224Updated last year
- 🧱 Modula software package☆321Updated 5 months ago
- Official JAX implementation of xLSTM including fast and efficient training and inference code. 7B model available at https://huggingface.…☆105Updated last year
- ☆133Updated last year
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆355Updated last year
- ☆237Updated last year
- For optimization algorithm research and development.☆556Updated last week
- Code repository for Black Mamba☆261Updated last year
- ☆288Updated last year
- Reverse Engineering the Abstraction and Reasoning Corpus☆330Updated 10 months ago
- Training small GPT-2 style models using Kolmogorov-Arnold networks.☆122Updated last year
- Simple, minimal implementation of the Mamba SSM in one pytorch file. Using logcumsumexp (Heisen sequence).☆129Updated last year
- DeMo: Decoupled Momentum Optimization☆198Updated last year
- The repository for the code of the UltraFastBERT paper☆519Updated last year
- Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.☆285Updated last year
- ☆109Updated 5 months ago
- Our solution for the arc challenge 2024☆188Updated 7 months ago
- Normalized Transformer (nGPT)☆196Updated last year
- Domain Specific Language for the Abstraction and Reasoning Corpus☆316Updated last year
- Accelerate, Optimize performance with streamlined training and serving options with JAX.☆330Updated 2 weeks ago
- Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"☆433Updated last year