mpezeshki / pytorch_forward_forward
Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation
β1,478Updated last year
Alternatives and similar repositories for pytorch_forward_forward:
Users that are interested in pytorch_forward_forward are comparing it to the libraries listed below
- π¦ Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorchβ2,125Updated 5 months ago
- Cramming the training of a (BERT-type) language model into limited compute.β1,331Updated 10 months ago
- β776Updated 2 weeks ago
- maximal update parametrization (Β΅P)β1,498Updated 9 months ago
- A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.β731Updated 11 months ago
- Tensors, for human consumptionβ1,246Updated 5 months ago
- Code for our NeurIPS 2022 paperβ367Updated 2 years ago
- The official implementation of βSophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-trainingββ957Updated last year
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)β1,252Updated 4 months ago
- functorch is JAX-like composable function transforms for PyTorch.β1,422Updated this week
- Reimplementation of Geoffrey Hinton's Forward-Forward Algorithmβ148Updated last year
- Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.β1,428Updated 8 months ago
- Pytorch library for fast transformer implementationsβ1,697Updated 2 years ago
- Convolutions for Sequence Modelingβ877Updated 10 months ago
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathwaysβ820Updated 2 years ago
- Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.β1,054Updated 2 weeks ago
- Transformer based on a variant of attention that is linear complexity in respect to sequence lengthβ758Updated 11 months ago
- The purpose of this repo is to make it easy to get started with JAX, Flax, and Haiku. It contains my "Machine Learning with JAX" series oβ¦β721Updated last year
- A concise but complete full-attention transformer with a set of promising experimental features from various papersβ5,248Updated this week
- Schedule-Free Optimization in PyTorchβ2,146Updated 2 weeks ago
- FFCV: Fast Forward Computer Vision (and other ML workloads!)β2,921Updated 10 months ago
- Code for visualizing the loss landscape of neural netsβ2,965Updated 3 years ago
- β531Updated last year
- Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"β477Updated 2 years ago
- torchview: visualize pytorch modelsβ908Updated this week
- A library to inspect and extract intermediate layers of PyTorch models.β473Updated 2 years ago
- Hopfield Networks is All You Needβ1,793Updated 2 years ago
- The WeightWatcher tool for predicting the accuracy of Deep Neural Networksβ1,577Updated 7 months ago
- Long Range Arena for Benchmarking Efficient Transformersβ751Updated last year
- Implementation of https://srush.github.io/annotated-s4β490Updated 2 years ago