samuela / git-re-basin
Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"
☆477Updated last year
Alternatives and similar repositories for git-re-basin:
Users that are interested in git-re-basin are comparing it to the libraries listed below
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆205Updated last year
- A library to inspect and extract intermediate layers of PyTorch models.☆472Updated 2 years ago
- Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch☆74Updated 2 years ago
- ☆200Updated 2 years ago
- Automatic gradient descent☆207Updated last year
- Named tensors with first-class dimensions for PyTorch☆321Updated last year
- D-Adaptation for SGD, Adam and AdaGrad☆515Updated last month
- Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory☆434Updated 6 months ago
- Train ImageNet *fast* in 500 lines of code with FFCV☆139Updated 9 months ago
- Official PyTorch Implementation of "Learning to Learn with Generative Models of Neural Network Checkpoints"☆337Updated 2 years ago
- Language Modeling with the H3 State Space Model☆516Updated last year
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- Unofficial JAX implementations of deep learning research papers☆153Updated 2 years ago
- Tensors, for human consumption☆1,192Updated 3 months ago
- ☆183Updated last year
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆210Updated this week
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆47Updated last year
- Code for our NeurIPS 2022 paper☆366Updated 2 years ago
- git extension for {collaborative, communal, continual} model development☆208Updated 3 months ago
- Editing Models with Task Arithmetic☆453Updated last year
- Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch☆251Updated 2 years ago
- Code release for "Dropout Reduces Underfitting"☆312Updated last year
- Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)☆340Updated 6 months ago
- Erasing concepts from neural representations with provable guarantees☆223Updated last month
- Framework code with wandb, checkpointing, logging, configs, experimental protocols. Useful for fine-tuning models or training from scratc…☆149Updated 2 years ago
- Tools for understanding how transformer predictions are built layer-by-layer☆477Updated 9 months ago
- ☆301Updated 8 months ago
- Probing the representations of Vision Transformers.☆321Updated 2 years ago
- Compare neural networks by their feature similarity☆353Updated last year
- Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order of magnitude using co…☆327Updated last year