samuela / git-re-basin
Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"
☆471Updated last year
Related projects ⓘ
Alternatives and complementary repositories for git-re-basin
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆203Updated last year
- Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch☆72Updated last year
- Named tensors with first-class dimensions for PyTorch☆322Updated last year
- D-Adaptation for SGD, Adam and AdaGrad☆502Updated 11 months ago
- A library to inspect and extract intermediate layers of PyTorch models.☆470Updated 2 years ago
- Code for our NeurIPS 2022 paper☆363Updated last year
- Automatic gradient descent☆206Updated last year
- ☆187Updated 2 years ago
- 94% on CIFAR-10 in 2.6 seconds 💨 96% in 27 seconds☆177Updated last week
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- Language Modeling with the H3 State Space Model☆513Updated last year
- Tensors, for human consumption☆1,113Updated 3 weeks ago
- Editing Models with Task Arithmetic☆429Updated 10 months ago
- maximal update parametrization (µP)☆1,402Updated 4 months ago
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆378Updated 5 months ago
- Simple and efficient RevNet-Library for PyTorch with XLA and DeepSpeed support and parameter offload☆124Updated 2 years ago
- git extension for {collaborative, communal, continual} model development☆205Updated this week
- Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)☆336Updated 3 months ago
- ☆508Updated 9 months ago
- Implementation of https://srush.github.io/annotated-s4☆469Updated last year
- Unofficial JAX implementations of deep learning research papers☆151Updated 2 years ago
- Code for Parameter Prediction for Unseen Deep Architectures (NeurIPS 2021)☆483Updated last year
- MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…☆333Updated 3 weeks ago
- Train ImageNet *fast* in 500 lines of code with FFCV☆136Updated 6 months ago
- ☆178Updated last year
- Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory☆428Updated 2 months ago
- Erasing concepts from neural representations with provable guarantees☆209Updated last week
- For optimization algorithm research and development.☆449Updated this week
- An alternative to convolution in neural networks☆251Updated 7 months ago
- Convolutions for Sequence Modeling☆869Updated 5 months ago