snimu / rebasinLinks
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
Alternatives and similar repositories for rebasin
Users that are interested in rebasin are comparing it to the libraries listed below
Sorting:
- Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch☆77Updated 2 years ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- Data for "Datamodels: Predicting Predictions with Training Data"☆97Updated 2 years ago
- Model Fusion via Optimal Transport, NeurIPS 2020☆149Updated 2 years ago
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆48Updated last year
- What do we learn from inverting CLIP models?☆55Updated last year
- ☆208Updated 2 years ago
- Latest Weight Averaging (NeurIPS HITY 2022)☆31Updated 2 years ago
- Codes for the paper "Optimizing Mode Connectivity via Neuron Alignment" from NeurIPS 2020.☆16Updated 4 years ago
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆80Updated last year
- Recycling diverse models☆45Updated 2 years ago
- ☆31Updated last year
- MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts (ICLR 2022)☆109Updated 2 years ago
- ☆71Updated 3 years ago
- Framework code with wandb, checkpointing, logging, configs, experimental protocols. Useful for fine-tuning models or training from scratc…☆151Updated 2 years ago
- Official Pytorch repo of CVPR'23 and NeurIPS'23 papers on understanding replication in diffusion models.☆108Updated last year
- ☆95Updated 2 years ago
- Personal implementation of ASIF by Antonio Norelli☆25Updated last year
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- PyTorch library for Active Fine-Tuning☆87Updated 5 months ago
- Code repository for the paper "Meta-Learning via Classifier(-free) Diffusion Guidance"☆32Updated 2 years ago
- A centralized place for deep thinking code and experiments☆85Updated last year
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆103Updated 2 years ago
- PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures (CVPR 2022)☆108Updated 3 years ago
- ☆81Updated last year
- Train ImageNet *fast* in 500 lines of code with FFCV☆144Updated last year
- ☆50Updated last year
- ☆129Updated 2 years ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆112Updated last month
- ☆185Updated last year