stanislavfort / dissect-git-re-basinLinks
Replicating and dissecting the git-re-basin project in one-click-replication Colabs
☆35Updated 3 years ago
Alternatives and similar repositories for dissect-git-re-basin
Users that are interested in dissect-git-re-basin are comparing it to the libraries listed below
Sorting:
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆68Updated last year
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆40Updated 2 years ago
- DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule☆63Updated 2 years ago
- Latest Weight Averaging (NeurIPS HITY 2022)☆31Updated 2 years ago
- ☆58Updated last year
- Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch☆77Updated 2 years ago
- Deep Networks Grok All the Time and Here is Why☆37Updated last year
- Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)☆63Updated 4 years ago
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆50Updated last year
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆85Updated last year
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆188Updated last week
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆52Updated 2 years ago
- Automatically take good care of your preemptible TPUs☆37Updated 2 years ago
- nanoGPT-like codebase for LLM training☆109Updated 5 months ago
- Implementation of Discrete Key / Value Bottleneck, in Pytorch☆88Updated 2 years ago
- supporting pytorch FSDP for optimizers☆83Updated 10 months ago
- ☆34Updated last year
- Official implementation for Equivariant Architectures for Learning in Deep Weight Spaces [ICML 2023]☆90Updated 2 years ago
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆80Updated 2 years ago
- Transformers with doubly stochastic attention☆49Updated 3 years ago
- Data for "Datamodels: Predicting Predictions with Training Data"☆97Updated 2 years ago
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆127Updated 2 years ago
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆59Updated 3 years ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- Python library for argument and configuration management☆55Updated 2 years ago
- These papers will provide unique insightful concepts that will broaden your perspective on neural networks and deep learning☆48Updated 2 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated last year
- Apply methods described in "Git Re-basin"-paper [1] to arbitrary models --- [1] Ainsworth et al. (https://arxiv.org/abs/2209.04836)☆15Updated this week
- ☆209Updated 3 years ago
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆101Updated 2 years ago