stanislavfort / dissect-git-re-basin
Replicating and dissecting the git-re-basin project in one-click-replication Colabs
☆36Updated 2 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
- Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch☆75Updated 2 years ago
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆47Updated last year
- ☆52Updated 6 months ago
- A centralized place for deep thinking code and experiments☆82Updated last year
- DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule☆60Updated last year
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆36Updated 2 years ago
- Apply methods described in "Git Re-basin"-paper [1] to arbitrary models --- [1] Ainsworth et al. (https://arxiv.org/abs/2209.04836)☆14Updated last week
- ☆33Updated 7 months ago
- ☆60Updated 3 years ago
- Latest Weight Averaging (NeurIPS HITY 2022)☆30Updated last year
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆80Updated last year
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆75Updated 8 months ago
- Source code of "What can linearized neural networks actually say about generalization?☆20Updated 3 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- nanoGPT-like codebase for LLM training☆94Updated 3 weeks ago
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆53Updated last year
- Transformers with doubly stochastic attention☆45Updated 2 years ago
- ☆51Updated 10 months ago
- Personal implementation of ASIF by Antonio Norelli☆25Updated 11 months ago
- Python library for argument and configuration management☆53Updated 2 years ago
- Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"☆41Updated 2 years ago
- Deep Networks Grok All the Time and Here is Why☆34Updated 11 months ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆65Updated 7 months ago
- Data for "Datamodels: Predicting Predictions with Training Data"☆97Updated last year
- Codebase for Mechanistic Mode Connectivity☆13Updated last year
- Easy Hypernetworks in Pytorch and Jax☆100Updated 2 years ago
- ☆40Updated 5 months ago
- Official repo for the paper "Weight-based Decomposition: A Case for Bilinear MLPs"☆20Updated 4 months ago
- ☆49Updated last year
- SGD with large step sizes learns sparse features [ICML 2023]☆32Updated 2 years ago