facebookresearch / dadaptationLinks
D-Adaptation for SGD, Adam and AdaGrad
☆522Updated 5 months ago
Alternatives and similar repositories for dadaptation
Users that are interested in dadaptation are comparing it to the libraries listed below
Sorting:
- The Prodigy optimizer and its variants for training neural networks.☆397Updated 5 months ago
- optimizer & lr scheduler & loss function collections in PyTorch☆304Updated 2 weeks ago
- A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model☆592Updated 6 months ago
- Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"☆480Updated 2 years ago
- Code for our NeurIPS 2022 paper☆368Updated 2 years ago
- 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch☆2,140Updated 6 months ago
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆379Updated last year
- A library to inspect and extract intermediate layers of PyTorch models.☆473Updated 3 years ago
- Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch☆252Updated 2 years ago
- ☆778Updated 3 weeks ago
- Unofficial Implementation of Consistency Models in pytorch☆257Updated 2 years ago
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆381Updated last year
- Memory Efficient Attention (O(sqrt(n)) for Jax and PyTorch☆184Updated 2 years ago
- Named tensors with first-class dimensions for PyTorch☆331Updated 2 years ago
- Code for NeurIPS 2022 Paper, "Poisson Flow Generative Models" (PFGM)☆861Updated 2 years ago
- Library for Jacobian descent with PyTorch. It enables the optimization of neural networks with multiple losses (e.g. multi-task learning)…☆246Updated last week
- Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"☆426Updated 6 months ago
- Efficient optimizers☆220Updated this week
- minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.☆464Updated 2 years ago
- Huggingface-compatible SDXL Unet implementation that is readily hackable☆424Updated last year
- Code release for "Dropout Reduces Underfitting"☆313Updated 2 years ago
- Diffusion attentive attribution maps for interpreting Stable Diffusion.☆764Updated last year
- The merlin dataloader lets you rapidly load tabular data for training deep leaning models with TensorFlow, PyTorch or JAX☆418Updated last year
- TensorDict is a pytorch dedicated tensor container.☆929Updated this week
- MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…☆385Updated this week
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch☆694Updated 6 months ago
- For optimization algorithm research and development.☆521Updated this week
- Universal Tensor Operations in Einstein-Inspired Notation for Python.☆381Updated 2 months ago
- Ranger deep learning optimizer rewrite to use newest components☆331Updated last year
- Official PyTorch Implementation of "Learning to Learn with Generative Models of Neural Network Checkpoints"☆341Updated 2 years ago