stanislavfort / dissect-git-re-basinLinks
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
Sorting:
- Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch☆77Updated 2 years ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆66Updated 10 months ago
- Latest Weight Averaging (NeurIPS HITY 2022)☆31Updated 2 years ago
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆180Updated last week
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆48Updated last year
- ☆208Updated 2 years ago
- A centralized place for deep thinking code and experiments☆85Updated last year
- nanoGPT-like codebase for LLM training☆102Updated 2 months ago
- ☆34Updated 10 months ago
- ☆53Updated 10 months ago
- Implementation of Discrete Key / Value Bottleneck, in Pytorch☆88Updated 2 years ago
- Transformers with doubly stochastic attention☆46Updated 2 years ago
- DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule☆63Updated last year
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆37Updated 2 years ago
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆80Updated last year
- Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)☆62Updated 4 years ago
- ☆33Updated 3 weeks ago
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆84Updated last year
- Official implementation for Equivariant Architectures for Learning in Deep Weight Spaces [ICML 2023]☆89Updated last year
- ☆51Updated last year
- ☆83Updated last year
- Python library for argument and configuration management☆54Updated 2 years ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆130Updated last year
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆54Updated 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 last week
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆59Updated 3 years ago
- [ICML 2024] SINGD: KFAC-like Structured Inverse-Free Natural Gradient Descent (http://arxiv.org/abs/2312.05705)☆22Updated 9 months ago
- Framework code with wandb, checkpointing, logging, configs, experimental protocols. Useful for fine-tuning models or training from scratc…☆151Updated 2 years ago
- These papers will provide unique insightful concepts that will broaden your perspective on neural networks and deep learning☆48Updated last year
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated last year