iShohei220 / adopt
Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"
☆425Updated 4 months ago
Alternatives and similar repositories for adopt:
Users that are interested in adopt are comparing it to the libraries listed below
- The AdEMAMix Optimizer: Better, Faster, Older.☆180Updated 7 months ago
- Efficient optimizers☆189Updated this week
- For optimization algorithm research and development.☆508Updated this week
- ☆150Updated 8 months ago
- Implementation of Diffusion Transformer (DiT) in JAX☆272Updated 10 months ago
- Implementation of the proposed minGRU in Pytorch☆286Updated last month
- Kolmogorov-Arnold Networks (KAN) using Chebyshev polynomials instead of B-splines.☆370Updated 11 months ago
- When it comes to optimizers, it's always better to be safe than sorry☆220Updated 3 weeks ago
- Annotated version of the Mamba paper☆483Updated last year
- Universal Tensor Operations in Einstein-Inspired Notation for Python.☆367Updated 2 weeks ago
- Library for Jacobian descent with PyTorch. It enables optimization of neural networks with multiple losses (e.g. multi-task learning).☆227Updated last week
- ☆175Updated 4 months ago
- Getting crystal-like representations with harmonic loss☆182Updated 3 weeks ago
- An implementation of PSGD Kron second-order optimizer for PyTorch☆89Updated 3 weeks ago
- Official JAX implementation of xLSTM including fast and efficient training and inference code. 7B model available at https://huggingface.…☆91Updated 3 months ago
- TensorHue is a Python library that allows you to visualize tensors right in your console, making understanding and debugging tensor conte…☆115Updated 2 months ago
- TensorDict is a pytorch dedicated tensor container.☆911Updated this week
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆230Updated last month
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆82Updated 2 months ago
- Scalable and Performant Data Loading☆237Updated last week
- Transform datasets at scale. Optimize datasets for fast AI model training.☆449Updated last week
- FastKAN: Very Fast Implementation of Kolmogorov-Arnold Networks (KAN)☆403Updated 10 months ago
- Access to free kaggle compute power from your command line☆29Updated last year
- Visualizations of the theory behind diffusion models.☆187Updated last year
- Simple and readable code for training and sampling from diffusion models☆483Updated 3 months ago
- Schedule-Free Optimization in PyTorch☆2,146Updated 2 weeks ago
- ⏰ AI conference deadline countdowns☆254Updated last month
- 🧱 Modula software package☆188Updated 3 weeks ago
- Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"☆555Updated 9 months ago
- PyTorch video decoding☆497Updated this week