iShohei220 / adoptLinks
Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"
☆433Updated last year
Alternatives and similar repositories for adopt
Users that are interested in adopt are comparing it to the libraries listed below
Sorting:
- For optimization algorithm research and development.☆556Updated last week
- The AdEMAMix Optimizer: Better, Faster, Older.☆186Updated last year
- Getting crystal-like representations with harmonic loss☆195Updated 9 months ago
- Library for Jacobian descent with PyTorch. It enables the optimization of neural networks with multiple losses (e.g. multi-task learning)…☆293Updated last week
- Efficient optimizers☆281Updated last month
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆344Updated 2 months ago
- ☆214Updated last year
- Annotated version of the Mamba paper☆493Updated last year
- ☆838Updated last month
- Universal Notation for Tensor Operations in Python.☆461Updated 9 months ago
- Implementation of Diffusion Transformer (DiT) in JAX☆305Updated last year
- Schedule-Free Optimization in PyTorch☆2,254Updated 8 months ago
- When it comes to optimizers, it's always better to be safe than sorry☆399Updated 3 months ago
- TensorHue is a Python library that allows you to visualize tensors right in your console, making understanding and debugging tensor conte…☆124Updated 11 months ago
- ☆314Updated last year
- ☆237Updated last year
- D-Adaptation for SGD, Adam and AdaGrad☆528Updated 11 months ago
- TensorDict is a pytorch dedicated tensor container.☆1,002Updated last week
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆126Updated last year
- Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"☆573Updated last year
- Simple, minimal implementation of the Mamba SSM in one pytorch file. Using logcumsumexp (Heisen sequence).☆129Updated last year
- An implementation of PSGD Kron second-order optimizer for PyTorch☆98Updated 5 months ago
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆293Updated 7 months ago
- Kolmogorov-Arnold Networks (KAN) using Chebyshev polynomials instead of B-splines.☆401Updated last year
- A repository for log-time feedforward networks☆224Updated last year
- Reliable, minimal and scalable library for pretraining foundation and world models☆117Updated this week
- Scalable and Performant Data Loading☆363Updated this week
- Implementation of the proposed minGRU in Pytorch☆318Updated last month
- Simple and readable code for training and sampling from diffusion models☆688Updated 7 months ago
- Speed up model training by fixing data loading.☆569Updated last week