mlfoundations / model-soupsLinks
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
☆497Updated 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…☆308Updated last year
- Robust fine-tuning of zero-shot models☆750Updated 3 years ago
- Code release for "Dropout Reduces Underfitting"☆315Updated 2 years ago
- Editing Models with Task Arithmetic☆511Updated last year
- ☆690Updated 2 weeks ago
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆336Updated 7 months ago
- Official code for "TOAST: Transfer Learning via Attention Steering"☆186Updated 2 years ago
- Official code for our CVPR'22 paper “Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space”☆250Updated 2 months ago
- PyTorch code for hierarchical k-means -- a data curation method for self-supervised learning☆219Updated last year
- Fine-tuning Vision Transformers on various classification datasets☆112Updated last year
- Compare neural networks by their feature similarity☆375Updated 2 years ago
- Collection of Tools and Papers related to Adapters / Parameter-Efficient Transfer Learning/ Fine-Tuning☆200Updated last year
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆370Updated last year
- ☆209Updated 2 years ago
- This repository contains the implementation for the paper "EMP-SSL: Towards Self-Supervised Learning in One Training Epoch."☆230Updated 2 years ago
- CLIP-like model evaluation☆787Updated 2 weeks ago
- DataComp: In search of the next generation of multimodal datasets☆746Updated 6 months ago
- Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)☆179Updated 5 months ago
- ☆186Updated last year
- ☆209Updated 3 years ago
- ☆259Updated 4 years ago
- [NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"☆320Updated last year
- Masked Siamese Networks for Label-Efficient Learning (https://arxiv.org/abs/2204.07141)☆461Updated 3 years ago
- Effective Data Augmentation With Diffusion Models☆266Updated last year
- Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(NeurIPS, 2021) paper☆776Updated 2 years ago
- Offsite-Tuning: Transfer Learning without Full Model☆382Updated last year
- ☆198Updated last year
- ☆189Updated 2 years ago
- ☆608Updated 3 months ago
- A collection of parameter-efficient transfer learning papers focusing on computer vision and multimodal domains.☆410Updated last year