nikhilvyas / SOAPLinks
☆215Updated 10 months ago
Alternatives and similar repositories for SOAP
Users that are interested in SOAP are comparing it to the libraries listed below
Sorting:
- Efficient optimizers☆265Updated last week
- supporting pytorch FSDP for optimizers☆84Updated 9 months ago
- 🧱 Modula software package☆277Updated last month
- Accelerated First Order Parallel Associative Scan☆190Updated last year
- ☆67Updated 10 months ago
- ☆58Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆164Updated 3 months ago
- An implementation of PSGD Kron second-order optimizer for PyTorch☆97Updated 2 months ago
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆301Updated 2 months ago
- The AdEMAMix Optimizer: Better, Faster, Older.☆186Updated last year
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆183Updated last week
- ☆120Updated 3 months ago
- ☆281Updated last year
- LoRA for arbitrary JAX models and functions☆142Updated last year
- A State-Space Model with Rational Transfer Function Representation.☆81Updated last year
- Maximal Update Parametrization (μP) with Flax & Optax.☆16Updated last year
- Pytorch-like dataloaders for JAX.☆94Updated 4 months ago
- A library for unit scaling in PyTorch☆130Updated 2 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆100Updated last year
- A MAD laboratory to improve AI architecture designs 🧪☆129Updated 9 months ago
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆292Updated 4 months ago
- ☆40Updated 3 weeks ago
- A simple library for scaling up JAX programs☆143Updated 11 months ago
- ☆89Updated last year
- WIP☆93Updated last year
- Official JAX implementation of xLSTM including fast and efficient training and inference code. 7B model available at https://huggingface.…☆103Updated 8 months ago
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆89Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆85Updated last year
- Supporting code for the blog post on modular manifolds.☆39Updated last week