vertaix / AlternatorsLinks
This repository contains the implementation of **Alternators**, a novel family of generative models for time-dependent data.
☆35Updated 4 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 9 months ago
- ☆30Updated last year
- Lightweight package that tracks and summarizes code changes using LLMs (Large Language Models)☆34Updated 7 months ago
- ☆33Updated 9 months ago
- ☆20Updated last year
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆102Updated 9 months ago
- A JAX implementation of the continuous time formulation of Consistency Models☆84Updated 2 years ago
- ☆24Updated last week
- Code for the paper Don't Pay Attention☆49Updated 3 weeks ago
- Latent Diffusion Language Models☆68Updated 2 years ago
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆25Updated 8 months ago
- ☆23Updated last year
- ☆32Updated 11 months ago
- Implementation of the proposed Spline-Based Transformer from Disney Research☆104Updated 11 months ago
- A scalable implementation of diffusion and flow-matching with XGBoost models, applied to calorimeter data.☆18Updated 11 months ago
- A State-Space Model with Rational Transfer Function Representation.☆82Updated last year
- σ-GPT: A New Approach to Autoregressive Models☆68Updated last year
- Getting crystal-like representations with harmonic loss☆193Updated 6 months ago
- ☆19Updated 5 months ago
- ☆24Updated last year
- ☆27Updated last year
- Implementation of Strassen attention, from Kozachinskiy et al. of National Center of AI in Chile☆41Updated 3 months ago
- Examples of apps built with Nendo, the AI Audio Tool Suite☆55Updated last year
- research impl of Native Sparse Attention (2502.11089)☆61Updated 8 months ago
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆91Updated 4 months ago
- DeMo: Decoupled Momentum Optimization☆194Updated 10 months ago
- Fork of Flame repo for training of some new stuff in development☆18Updated last week
- https://hf.co/hexgrad/Kokoro-82M☆14Updated 7 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆106Updated 7 months ago