facebookresearch / dadaptation
D-Adaptation for SGD, Adam and AdaGrad
☆510Updated last year
Alternatives and similar repositories for dadaptation:
Users that are interested in dadaptation are comparing it to the libraries listed below
- The Prodigy optimizer and its variants for training neural networks.☆364Updated last week
- optimizer & lr scheduler & loss function collections in PyTorch☆259Updated this week
- Code for our NeurIPS 2022 paper☆366Updated 2 years ago
- A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model☆548Updated last month
- 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch☆2,080Updated last month
- Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"☆477Updated last year
- Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch☆250Updated 2 years ago
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch☆609Updated last month
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆378Updated 7 months ago
- A library to inspect and extract intermediate layers of PyTorch models.☆470Updated 2 years ago
- Named tensors with first-class dimensions for PyTorch☆322Updated last year
- Tensors, for human consumption☆1,178Updated last month
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆370Updated last year
- torchview: visualize pytorch models☆857Updated 2 months ago
- For optimization algorithm research and development.☆484Updated this week
- Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in P…☆197Updated 11 months ago
- MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…☆345Updated this week
- Unofficial Implementation of Consistency Models in pytorch☆255Updated last year
- minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.☆444Updated last year
- Language Modeling with the H3 State Space Model☆516Updated last year
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆941Updated 11 months ago
- Huggingface-compatible SDXL Unet implementation that is readily hackable☆405Updated last year
- A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.☆696Updated 8 months ago
- ☆759Updated last week
- Code for NeurIPS 2022 Paper, "Poisson Flow Generative Models" (PFGM)☆858Updated last year
- Code release for "Dropout Reduces Underfitting"☆311Updated last year
- Pretrained deep learning models for Jax/Flax: StyleGAN2, GPT2, VGG, ResNet, etc.☆240Updated last year
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆204Updated last year
- ☆467Updated last year
- TensorDict is a pytorch dedicated tensor container.☆862Updated this week