Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam
☆86Jul 28, 2024Updated last year
Alternatives and similar repositories for ezmup
Users that are interested in ezmup are comparing it to the libraries listed below
Sorting:
- [Corca / OR] Solver for Multi-dimensional Multi-demand Quadratic Knapsack Problems☆12Mar 22, 2022Updated 3 years ago
- These papers will provide unique insightful concepts that will broaden your perspective on neural networks and deep learning☆48Sep 3, 2023Updated 2 years ago
- ☆32Jan 1, 2024Updated 2 years ago
- ☆27May 3, 2024Updated last year
- ☆30Dec 2, 2024Updated last year
- ☆33Nov 4, 2024Updated last year
- ☆16Jun 5, 2022Updated 3 years ago
- Minimal implementation of scalable rectified flow transformers, based on SD3's approach☆634Jul 1, 2024Updated last year
- Restaurant Recommender System☆15May 5, 2022Updated 3 years ago
- ☆34Sep 10, 2024Updated last year
- Code for the paper "Function-Space Learning Rates"☆25Jun 3, 2025Updated 9 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Apr 17, 2024Updated last year
- Minimal (truly) muP implementation, consistent with TP4 and TP5 papers notation☆14Jan 2, 2026Updated 2 months ago
- 7th place solution to RecSys Challenge 2023 by Corca☆10Jan 8, 2024Updated 2 years ago
- ☆28Oct 7, 2025Updated 4 months ago
- Maximal Update Parametrization (μP) with Flax & Optax.☆16Dec 27, 2023Updated 2 years ago
- A library for unit scaling in PyTorch☆133Jul 11, 2025Updated 7 months ago
- Unofficial Implementation of Consistency Models in pytorch☆260Mar 7, 2023Updated 2 years ago
- WIP☆94Aug 13, 2024Updated last year
- LCM Full Cycle Trainer for Ostris - Ai Toolkit☆16Aug 20, 2024Updated last year
- ☆16Jul 8, 2024Updated last year
- Efficient optimizers☆285Dec 20, 2025Updated 2 months ago
- supporting pytorch FSDP for optimizers☆84Dec 8, 2024Updated last year
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆57Mar 10, 2025Updated 11 months ago
- ☆86Mar 1, 2023Updated 3 years ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆187Jan 19, 2026Updated last month
- Train VAE like a boss☆313Oct 21, 2024Updated last year
- A set of Python scripts that makes your experience on TPU better☆56Sep 18, 2025Updated 5 months ago
- ☆39Apr 27, 2024Updated last year
- ☆23Jun 18, 2024Updated last year
- ☆93Jul 5, 2024Updated last year
- This action allows caching dependencies and build outputs to improve workflow execution time on self hosted machine.☆65Jun 6, 2025Updated 8 months ago
- 🧱 Modula software package☆323Aug 18, 2025Updated 6 months ago
- JAX Scalify: end-to-end scaled arithmetics☆18Oct 30, 2024Updated last year
- ☆24Jun 4, 2024Updated last year
- maximal update parametrization (µP)☆1,686Jul 17, 2024Updated last year
- Huggingface-compatible SDXL Unet implementation that is readily hackable☆435Aug 9, 2023Updated 2 years ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆92Oct 30, 2024Updated last year
- Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.☆32Jun 5, 2025Updated 8 months ago