mpezeshki / pytorch_forward_forward

Related projects: ⓘ

• google / learned_optimization
  ☆742Updated 5 months ago
• tysam-code / hlb-CIFAR10
  Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
  ☆1,213Updated 10 months ago
• state-spaces / s4
  Structured state space sequence models
  ☆2,361Updated 2 months ago
• xl0 / lovely-tensors
  Tensors, for human consumption
  ☆1,096Updated 2 weeks ago
• JonasGeiping / cramming
  Cramming the training of a (BERT-type) language model into limited compute.
  ☆1,284Updated 3 months ago
• ml-jku / hopfield-layers
  Hopfield Networks is All You Need
  ☆1,660Updated last year
• lucidrains / lion-pytorch
  🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
  ☆2,002Updated 3 months ago
• microsoft / mup
  maximal update parametrization (µP)
  ☆1,334Updated 2 months ago
• Liuhong99 / Sophia
  The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”
  ☆931Updated 7 months ago
• kach / gradient-descent-the-ultimate-optimizer
  Code for our NeurIPS 2022 paper
  ☆360Updated last year
• HazyResearch / safari
  Convolutions for Sequence Modeling
  ☆861Updated 3 months ago
• tanelp / tiny-diffusion
  A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.
  ☆633Updated 4 months ago
• lucidrains / x-transformers
  A concise but complete full-attention transformer with a set of promising experimental features from various papers
  ☆4,573Updated last week
• microsoft / torchscale
  Foundation Architecture for (M)LLMs
  ☆3,003Updated 5 months ago
• nnaisense / evotorch
  Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.
  ☆999Updated 2 weeks ago
• google-deepmind / dm-haiku
  JAX-based neural network library
  ☆2,860Updated last week
• srush / annotated-s4
  Implementation of https://srush.github.io/annotated-s4
  ☆456Updated last year
• pytorch / functorch
  functorch is JAX-like composable function transforms for PyTorch.
  ☆1,389Updated this week
• n2cholas / awesome-jax
  JAX - A curated list of resources https://github.com/google/jax
  ☆1,468Updated 2 months ago
• karpathy / arxiv-sanity-lite
  arxiv-sanity lite: tag arxiv papers of interest get recommendations of similar papers in a nice UI using SVMs over tfidf feature vectors …
  ☆1,156Updated last year
• google / ml_collections
  ML Collections is a library of Python Collections designed for ML use cases.
  ☆879Updated last month
• patrick-kidger / torchtyping
  Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.
  ☆1,382Updated last month
• google-deepmind / alphatensor
  ☆2,670Updated 4 months ago
• idiap / fast-transformers
  Pytorch library for fast transformer implementations
  ☆1,621Updated last year
• CalculatedContent / WeightWatcher
  The WeightWatcher tool for predicting the accuracy of Deep Neural Networks
  ☆1,438Updated last week
• HazyResearch / H3
  Language Modeling with the H3 State Space Model
  ☆509Updated 11 months ago
• mert-kurttutan / torchview
  torchview: visualize pytorch models
  ☆793Updated 4 months ago
• clementchadebec / benchmark_VAE
  Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)
  ☆1,769Updated last month
• kyegomez / Sophia
  Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.
  ☆374Updated 3 months ago
• google-research / long-range-arena
  Long Range Arena for Benchmarking Efficient Transformers
  ☆711Updated 9 months ago