samuela / git-re-basin
Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"
☆479Updated 2 years ago
Alternatives and similar repositories for git-re-basin:
Users that are interested in git-re-basin are comparing it to the libraries listed below
- Language Modeling with the H3 State Space Model☆520Updated last year
- A library to inspect and extract intermediate layers of PyTorch models.☆473Updated 2 years ago
- Named tensors with first-class dimensions for PyTorch☆320Updated last year
- D-Adaptation for SGD, Adam and AdaGrad☆521Updated 3 months ago
- Code for our NeurIPS 2022 paper☆367Updated 2 years ago
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆207Updated last year
- ☆205Updated 2 years ago
- ☆532Updated last year
- Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch☆75Updated 2 years ago
- Editing Models with Task Arithmetic☆469Updated last year
- git extension for {collaborative, communal, continual} model development☆211Updated 5 months ago
- Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory☆436Updated 8 months ago
- Implementation of https://srush.github.io/annotated-s4☆494Updated 2 years ago
- minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.☆458Updated last year
- ☆376Updated last year
- Tensors, for human consumption☆1,249Updated 5 months ago
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆233Updated 2 months ago
- Pretrained deep learning models for Jax/Flax: StyleGAN2, GPT2, VGG, ResNet, etc.☆251Updated last month
- Convolutions for Sequence Modeling☆883Updated 10 months ago
- Diffusers-Interpret 🤗🧨🕵️♀️: Model explainability for 🤗 Diffusers. Get explanations for your generated images.☆276Updated 2 years ago
- Simple and efficient RevNet-Library for PyTorch with XLA and DeepSpeed support and parameter offload☆127Updated 2 years ago
- maximal update parametrization (µP)☆1,500Updated 9 months ago
- ☆224Updated 2 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆490Updated 11 months ago
- Erasing concepts from neural representations with provable guarantees☆228Updated 3 months ago
- Unofficial JAX implementations of deep learning research papers☆156Updated 2 years ago
- Train ImageNet *fast* in 500 lines of code with FFCV☆142Updated 11 months ago
- BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.☆581Updated 4 months ago
- Official PyTorch Implementation of "Learning to Learn with Generative Models of Neural Network Checkpoints"☆340Updated 2 years ago
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆47Updated last year