vertaix / AlternatorsLinks
This repository contains the implementation of **Alternators**, a novel family of generative models for time-dependent data.
☆35Updated 3 months ago
Alternatives and similar repositories for Alternators
Users that are interested in Alternators are comparing it to the libraries listed below
Sorting:
- Using JAX to generate piano music as MIDI☆39Updated last year
- Focused on fast experimentation and simplicity☆75Updated 8 months ago
- ☆30Updated 11 months ago
- Code for the paper Don't Pay Attention☆48Updated 2 months ago
- ☆24Updated 4 months ago
- Lightweight package that tracks and summarizes code changes using LLMs (Large Language Models)☆34Updated 6 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆101Updated 8 months ago
- ☆20Updated last year
- Examples of apps built with Nendo, the AI Audio Tool Suite☆55Updated last year
- ☆23Updated last year
- Basic world models☆23Updated last week
- ☆32Updated 10 months ago
- A JAX implementation of the continuous time formulation of Consistency Models☆85Updated 2 years ago
- ☆33Updated 8 months ago
- σ-GPT: A New Approach to Autoregressive Models☆67Updated last year
- CLIP Guided Diffusion☆69Updated last year
- Implementation of the proposed Spline-Based Transformer from Disney Research☆103Updated 9 months ago
- A State-Space Model with Rational Transfer Function Representation.☆79Updated last year
- ☆27Updated last year
- ☆24Updated last year
- a new family of super small music generation models focusing on experimental music and latent space exploration capabilities☆35Updated last year
- Getting crystal-like representations with harmonic loss☆194Updated 5 months ago
- Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.☆68Updated 3 weeks ago
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆25Updated 7 months ago
- ☆34Updated 11 months ago
- ☆28Updated last month
- research impl of Native Sparse Attention (2502.11089)☆60Updated 6 months ago
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆89Updated 2 months ago
- ☆107Updated last year
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆105Updated 6 months ago