Alternatives and similar repositories for dadaptation:

Users that are interested in dadaptation are comparing it to the libraries listed below

• konstmish / prodigy
  The Prodigy optimizer and its variants for training neural networks.
  ☆368Updated 3 weeks ago
• kach / gradient-descent-the-ultimate-optimizer
  Code for our NeurIPS 2022 paper
  ☆366Updated 2 years ago
• samuela / git-re-basin
  Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"
  ☆477Updated last year
• lucidrains / Adan-pytorch
  Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch
  ☆251Updated 2 years ago
• lucidrains / ema-pytorch
  A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model
  ☆557Updated 2 months ago
• lucidrains / lion-pytorch
  🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
  ☆2,094Updated 2 months ago
• kozistr / pytorch_optimizer
  optimizer & lr scheduler & loss function collections in PyTorch
  ☆268Updated this week
• lucidrains / memory-efficient-attention-pytorch
  Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"
  ☆369Updated last year
• cccntu / minLoRA
  minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.
  ☆448Updated last year
• OATML / RHO-Loss
  ☆199Updated 2 years ago
• facebookresearch / torchdim
  Named tensors with first-class dimensions for PyTorch
  ☆321Updated last year
• google / learned_optimization
  ☆761Updated 3 weeks ago
• cloneofsimo / consistency_models
  Unofficial Implementation of Consistency Models in pytorch
  ☆255Updated last year
• AminRezaei0x443 / memory-efficient-attention
  Memory Efficient Attention (O(sqrt(n)) for Jax and PyTorch
  ☆180Updated 2 years ago
• facebookresearch / dropout
  Code release for "Dropout Reduces Underfitting"
  ☆311Updated last year
• archinetai / surgeon-pytorch
  A library to inspect and extract intermediate layers of PyTorch models.
  ☆471Updated 2 years ago
• tanelp / tiny-diffusion
  A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.
  ☆702Updated 9 months ago
• iShohei220 / adopt
  Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"
  ☆416Updated 2 months ago
• TorchJD / torchjd
  Library for Jacobian descent with PyTorch. It enables optimization of neural networks with multiple losses (e.g. multi-task learning).
  ☆202Updated this week
• hristo-vrigazov / mmap.ninja
  Memory mapped numpy arrays of varying shapes
  ☆292Updated 7 months ago
• facebookresearch / optimizers
  For optimization algorithm research and development.
  ☆490Updated this week
• sail-sg / Adan
  Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
  ☆774Updated 7 months ago
• Liuhong99 / Sophia
  The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”
  ☆949Updated last year
• mlcommons / algorithmic-efficiency
  MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…
  ☆360Updated this week
• lucidrains / flash-cosine-sim-attention
  Implementation of fused cosine similarity attention in the same style as Flash Attention
  ☆210Updated 2 years ago
• HomebrewML / HeavyBall
  Efficient optimizers
  ☆169Updated this week
• facebookresearch / FFCV-SSL
  FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.
  ☆204Updated last year
• kyegomez / Sophia
  Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.
  ☆378Updated 8 months ago
• JoaoLages / diffusers-interpret
  Diffusers-Interpret 🤗🧨🕵️‍♀️: Model explainability for 🤗 Diffusers. Get explanations for your generated images.
  ☆274Updated 2 years ago
• lucidrains / recurrent-interface-network-pytorch
  Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in P…
  ☆200Updated last year