sidak / otfusion
Model Fusion via Optimal Transport, NeurIPS 2020
☆144Updated 2 years ago
Alternatives and similar repositories for otfusion:
Users that are interested in otfusion are comparing it to the libraries listed below
- Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch☆75Updated 2 years ago
- Official implementation for Equivariant Architectures for Learning in Deep Weight Spaces [ICML 2023]☆89Updated last year
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆47Updated last year
- Model Zoos published at the NeurIPS 2022 Dataset & Benchmark track: "Model Zoos: A Dataset of Diverse Populations of Neural Network Model…☆55Updated last year
- The official PyTorch implementation - Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from t…☆78Updated 2 years ago
- ☆58Updated last year
- Code for the paper "Efficient Dataset Distillation using Random Feature Approximation"☆37Updated 2 years ago
- Source code of "What can linearized neural networks actually say about generalization?☆20Updated 3 years ago
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆80Updated last year
- ☆113Updated last year
- ☆66Updated 3 years ago
- Prospect Pruning: Finding Trainable Weights at Initialization Using Meta-Gradients☆31Updated 3 years ago
- Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"☆36Updated 2 years ago
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆101Updated last year
- ☆107Updated last year
- Data-efficient Training of Machine Learning Models☆63Updated 4 years ago
- Towards Understanding the Mixture-of-Experts Layer in Deep Learning☆28Updated last year
- ☆38Updated 5 months ago
- Sharpness-Aware Minimization Leads to Low-Rank Features [NeurIPS 2023]☆28Updated last year
- Deep Learning & Information Bottleneck☆60Updated last year
- source code for paper "Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models"☆24Updated 10 months ago
- Tilted Empirical Risk Minimization (ICLR '21)☆59Updated last year
- ☆45Updated 2 years ago
- A simple PyTorch implementation of influence functions.☆85Updated 10 months ago
- Benchmark for Natural Temporal Distribution Shift (NeurIPS 2022)☆66Updated 2 years ago
- Code for "Surgical Fine-Tuning Improves Adaptation to Distribution Shifts" published at ICLR 2023☆29Updated last year
- Build PyTorch CIFAR100 using coarse labels☆38Updated 4 years ago
- Code release for the paper Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning☆30Updated 2 years ago
- Official implementation of ORCA proposed in the paper "Cross-Modal Fine-Tuning: Align then Refine"☆71Updated last year