mlfoundations / model-soupsLinks
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
☆480Updated last year
Alternatives and similar repositories for model-soups
Users that are interested in model-soups are comparing it to the libraries listed below
Sorting:
- A framework for merging models solving different tasks with different initializations into one multi-task model without any additional tr…☆306Updated last year
- Robust fine-tuning of zero-shot models☆730Updated 3 years ago
- Code release for "Dropout Reduces Underfitting"☆314Updated 2 years ago
- This repository contains the implementation for the paper "EMP-SSL: Towards Self-Supervised Learning in One Training Epoch."☆229Updated 2 years ago
- Official code for our CVPR'22 paper “Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space”☆250Updated this week
- ☆667Updated 3 weeks ago
- Fine-tuning Vision Transformers on various classification datasets☆109Updated 11 months ago
- Editing Models with Task Arithmetic☆495Updated last year
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆313Updated 4 months ago
- ☆206Updated last year
- PyTorch code for hierarchical k-means -- a data curation method for self-supervised learning☆172Updated last year
- Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)☆174Updated 2 months ago
- Collection of Tools and Papers related to Adapters / Parameter-Efficient Transfer Learning/ Fine-Tuning☆197Updated last year
- Compare neural networks by their feature similarity☆370Updated 2 years ago
- Official code for "TOAST: Transfer Learning via Attention Steering"☆188Updated 2 years ago
- CLIP-like model evaluation☆759Updated 2 weeks ago
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆359Updated last year
- Masked Siamese Networks for Label-Efficient Learning (https://arxiv.org/abs/2204.07141)☆456Updated 3 years ago
- Learning from synthetic data - code and models☆320Updated last year
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆207Updated 2 years ago
- A method to increase the speed and lower the memory footprint of existing vision transformers.☆1,083Updated last year
- A collection of parameter-efficient transfer learning papers focusing on computer vision and multimodal domains.☆406Updated 11 months ago
- DataComp: In search of the next generation of multimodal datasets☆736Updated 4 months ago
- ☆248Updated 3 years ago
- [ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decode…☆867Updated 2 years ago
- Code for ICML 2022 paper "Out-of-distribution Detection with Deep Nearest Neighbors"☆186Updated last year
- ☆182Updated 11 months ago
- (ICLR 2023) Official PyTorch implementation of "What Do Self-Supervised Vision Transformers Learn?"☆111Updated last year
- When do we not need larger vision models?☆407Updated 6 months ago
- EsViT: Efficient self-supervised Vision Transformers☆412Updated 2 years ago