kozistr / pytorch_optimizer
optimizer & lr scheduler & loss function collections in PyTorch
☆289Updated this week
Alternatives and similar repositories for pytorch_optimizer:
Users that are interested in pytorch_optimizer are comparing it to the libraries listed below
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆377Updated last year
- A library that contains a rich collection of performant PyTorch model metrics, a simple interface to create new metrics, a toolkit to fac…☆229Updated 3 months ago
- ☆205Updated 2 years ago
- A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model☆571Updated 4 months ago
- D-Adaptation for SGD, Adam and AdaGrad☆520Updated 3 months ago
- When it comes to optimizers, it's always better to be safe than sorry☆220Updated 3 weeks ago
- Implementation of Linformer for Pytorch☆279Updated last year
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆213Updated 2 years ago
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆120Updated 8 months ago
- Ranger deep learning optimizer rewrite to use newest components☆329Updated last year
- Implementation of ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks, ICML 2021.☆141Updated 3 years ago
- Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch☆251Updated 2 years ago
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch☆666Updated 4 months ago
- Code release for "Dropout Reduces Underfitting"☆313Updated last year
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆203Updated last year
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆380Updated 10 months ago
- FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores☆317Updated 3 months ago
- Efficient optimizers☆189Updated this week
- ☆175Updated 4 months ago
- An implementation of local windowed attention for language modeling☆443Updated 3 months ago
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆328Updated 10 months ago
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time☆458Updated 9 months ago
- ☆457Updated 2 years ago
- Library for Jacobian descent with PyTorch. It enables optimization of neural networks with multiple losses (e.g. multi-task learning).☆227Updated last week
- The AdEMAMix Optimizer: Better, Faster, Older.☆180Updated 7 months ago
- Adaptive Gradient Clipping☆130Updated 2 years ago
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆283Updated 3 weeks ago
- Named tensors with first-class dimensions for PyTorch☆320Updated last year
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆103Updated 4 months ago
- Code for our NeurIPS 2022 paper☆367Updated 2 years ago