mryab / learning-at-home
"Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts" (NeurIPS 2020), original PyTorch implementation
☆54Updated 4 years ago
Alternatives and similar repositories for learning-at-home:
Users that are interested in learning-at-home are comparing it to the libraries listed below
- Memory-efficient transformer. Work in progress.☆19Updated 2 years ago
- ☆41Updated last year
- "Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices", official implementation☆29Updated last month
- Code for the paper "Secure Distributed Training at Scale" (ICML 2022)☆15Updated last month
- A GPT, made only of MLPs, in Jax☆57Updated 3 years ago
- Official code for paper "Non-Adversarial Image Synthesis with Generative Latent Nearest Neighbors"☆28Updated 5 years ago
- Implementation of Kronecker Attention in Pytorch☆18Updated 4 years ago
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆48Updated 3 years ago
- Python library for argument and configuration management☆53Updated 2 years ago
- Official code for "Distributed Deep Learning in Open Collaborations" (NeurIPS 2021)☆116Updated 3 years ago
- Latest Weight Averaging (NeurIPS HITY 2022)☆28Updated last year
- Compression schema for gradients of activations in backward pass☆44Updated last year
- SelectiveBackprop accelerates training by dynamically prioritizing useful examples with high loss☆32Updated 5 years ago
- PyTorch implementation of HashedNets☆36Updated last year
- A case study of efficient training of large language models using commodity hardware.☆68Updated 2 years ago
- Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper☆80Updated 3 years ago
- Official repository for the paper "Going Beyond Linear Transformers with Recurrent Fast Weight Programmers" (NeurIPS 2021)☆48Updated last year
- Learned Hyperparameter Optimizers☆58Updated 3 years ago
- Learning to Initialize Neural Networks for Stable and Efficient Training☆138Updated 2 years ago
- Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural netwo…☆66Updated 3 months ago
- [NeurIPS 2022] DataMUX: Data Multiplexing for Neural Networks☆60Updated 2 years ago
- Training a model similar to OpenAI DALL-E with volunteers from all over the Internet using hivemind and dalle-pytorch (NeurIPS 2021 demo)☆26Updated last year
- Another attempt at a long-context / efficient transformer by me☆37Updated 2 years ago
- Collaborative inference of latent diffusion via hivemind☆12Updated last year
- A collection of optimizers, some arcane others well known, for Flax.☆29Updated 3 years ago
- GPT, but made only out of MLPs☆88Updated 3 years ago
- Pretrained TorchVision models on CIFAR10 dataset (with weights)☆24Updated 4 years ago
- Contains my experiments with the `big_vision` repo to train ViTs on ImageNet-1k.☆22Updated 2 years ago
- [ICLR 2021] Beyond Categorical Label Representations for Image Classification☆25Updated 3 years ago
- Factorized Neural Layers☆27Updated last year