a-r-r-o-w / kanformerLinks
Naively combining transformers and Kolmogorov-Arnold Networks to learn and experiment
☆35Updated 10 months ago
Alternatives and similar repositories for kanformer
Users that are interested in kanformer are comparing it to the libraries listed below
Sorting:
- PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"☆171Updated 2 months ago
- A single repo with all scripts and utils to train / fine-tune the Mamba model with or without FIM☆55Updated last year
- A modified CNN architecture using Kolmogorov-Arnold Networks☆80Updated last year
- ☆133Updated last year
- KAN for Vision Transformer☆248Updated 8 months ago
- Benchmark for efficiency in memory and time of different KAN implementations.☆126Updated 10 months ago
- Implementation of Griffin from the paper: "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"☆55Updated 2 months ago
- Integrating Mamba/SSMs with Transformer for Enhanced Long Context and High-Quality Sequence Modeling☆196Updated 2 months ago
- First-principle implementations of groundbreaking AI algorithms using a wide range of deep learning frameworks, accompanied by supporting…☆170Updated this week
- my attempts at implementing various bits of Sepp Hochreiter's new xLSTM architecture☆130Updated last year
- Pytorch (Lightning) implementation of the Mamba model☆29Updated 2 months ago
- Collection of tests performed during the study of the new Kolmogorov-Arnold Neural Networks (KAN)☆39Updated 4 months ago
- Benchmarking and Testing FastKAN☆78Updated last year
- ☆18Updated 8 months ago
- Code repository for Black Mamba☆247Updated last year
- An easy to use PyTorch implementation of the Kolmogorov Arnold Network and a few novel variations☆183Updated 7 months ago
- ☆92Updated last year
- Official PyTorch Implementation of "The Hidden Attention of Mamba Models"☆223Updated last year
- Implementation of xLSTM in Pytorch from the paper: "xLSTM: Extended Long Short-Term Memory"☆119Updated 2 months ago
- Kolmogorov-Arnold Networks (KAN) using Chebyshev polynomials instead of B-splines.☆380Updated last year
- Cuda implementation of Extended Long Short Term Memory (xLSTM) with C++ and PyTorch ports☆87Updated last year
- ☆39Updated last month
- Trying out the Mamba architecture on small examples (cifar-10, shakespeare char level etc.)☆46Updated last year
- Variations of Kolmogorov-Arnold Networks☆115Updated last year
- This repository contains a better implementation of Kolmogorov-Arnold networks☆62Updated 3 weeks ago
- A simple but robust PyTorch implementation of RetNet from "Retentive Network: A Successor to Transformer for Large Language Models" (http…☆106Updated last year
- Kolmogorov–Arnold Networks with modified activation (using MLP to represent the activation)☆105Updated 7 months ago
- Notes on the Mamba and the S4 model (Mamba: Linear-Time Sequence Modeling with Selective State Spaces)☆169Updated last year
- Awesome list of papers that extend Mamba to various applications.☆133Updated 2 weeks ago
- ☆63Updated 4 months ago