cloneofsimo / ezmupLinks
Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam
☆85Updated last year
Alternatives and similar repositories for ezmup
Users that are interested in ezmup are comparing it to the libraries listed below
Sorting:
- These papers will provide unique insightful concepts that will broaden your perspective on neural networks and deep learning☆48Updated 2 years ago
- WIP☆93Updated last year
- supporting pytorch FSDP for optimizers☆84Updated last year
- ☆53Updated 2 years ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- ☆92Updated last year
- ☆34Updated last year
- Focused on fast experimentation and simplicity☆79Updated last year
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆56Updated 10 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆181Updated 6 months ago
- ☆30Updated last year
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆53Updated 2 years ago
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆126Updated last year
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆37Updated 3 years ago
- ☆23Updated last year
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆132Updated 2 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆100Updated last year
- Mixture of A Million Experts☆52Updated last year
- research impl of Native Sparse Attention (2502.11089)☆63Updated 10 months ago
- Language models scale reliably with over-training and on downstream tasks☆100Updated last year
- ☆53Updated last year
- A library for unit scaling in PyTorch☆133Updated 6 months ago
- ☆124Updated last year
- Automatically take good care of your preemptible TPUs☆37Updated 2 years ago
- LoRA for arbitrary JAX models and functions☆143Updated last year
- ☆235Updated last year
- Accelerated First Order Parallel Associative Scan☆192Updated last week
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆224Updated last year
- A JAX implementation of the continuous time formulation of Consistency Models☆85Updated 2 years ago
- Efficient optimizers☆280Updated 3 weeks ago