Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
☆507Jul 15, 2024Updated 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:
- Robust fine-tuning of zero-shot models☆760Apr 29, 2022Updated 3 years ago
- DiWA: Diverse Weight Averaging for Out-of-Distribution Generalization☆31Jan 31, 2023Updated 3 years ago
- Editing Models with Task Arithmetic☆535Jan 11, 2024Updated 2 years ago
- Model Stock: All we need is just a few fine-tuned models☆129Aug 9, 2025Updated 6 months ago
- ☆210Feb 3, 2024Updated 2 years ago
- ModelSoups for Tensorflow2 and Torch☆50Apr 27, 2022Updated 3 years ago
- BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training☆401Oct 23, 2024Updated last year
- ☆80Mar 17, 2022Updated 3 years ago
- Patching open-vocabulary models by interpolating weights☆91Sep 28, 2023Updated 2 years ago
- Host CIFAR-10.2 Data Set☆13Sep 22, 2021Updated 4 years ago
- NeurIPS 2025 Spotlight; ICLR2024 Spotlight; CVPR 2024; EMNLP 2024☆1,815Nov 27, 2025Updated 3 months ago
- DataComp: In search of the next generation of multimodal datasets☆772Apr 28, 2025Updated 10 months ago
- An open source implementation of CLIP.☆13,430Updated this week
- Tools for merging pretrained large language models.☆6,826Updated this week
- PoolFormer: MetaFormer Is Actually What You Need for Vision (CVPR 2022 Oral)☆1,367Jun 1, 2024Updated last year
- [ICLR 2022] "As-ViT: Auto-scaling Vision Transformers without Training" by Wuyang Chen, Wei Huang, Xianzhi Du, Xiaodan Song, Zhangyang Wa…☆76Feb 21, 2022Updated 4 years ago
- Source code for "Gradient Based Memory Editing for Task-Free Continual Learning", 4th Lifelong ML Workshop@ICML 2020☆17Dec 8, 2022Updated 3 years ago
- [ECCV 2022]Code for paper "DaViT: Dual Attention Vision Transformer"☆374Feb 13, 2024Updated 2 years ago
- Code release for SLIP Self-supervision meets Language-Image Pre-training☆787Feb 9, 2023Updated 3 years ago
- Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)☆359Apr 17, 2025Updated 10 months ago
- CLIP-like model evaluation☆804Jan 15, 2026Updated last month
- [ECCV2022] New benchmark for evaluating pre-trained model; New supervised contrastive learning framework.☆110Dec 8, 2023Updated 2 years ago
- A method to increase the speed and lower the memory footprint of existing vision transformers.☆1,171Jun 17, 2024Updated last year
- EVA Series: Visual Representation Fantasies from BAAI☆2,648Aug 1, 2024Updated last year
- [NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"☆319Jun 3, 2024Updated last year
- ☆110Sep 20, 2023Updated 2 years ago
- Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm☆675Sep 19, 2022Updated 3 years ago
- Official Implementation of SWAD (NeurIPS 2021)☆170Dec 10, 2022Updated 3 years ago
- Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.☆3,371May 19, 2025Updated 9 months ago
- Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"☆506Mar 7, 2023Updated 2 years ago
- Official DeiT repository☆4,325Mar 15, 2024Updated last year
- ☆26Feb 27, 2022Updated 4 years ago
- COYO-700M: Large-scale Image-Text Pair Dataset☆1,252Nov 30, 2022Updated 3 years ago
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆112Jun 8, 2023Updated 2 years ago
- Code release for ConvNeXt model☆6,300Jan 8, 2023Updated 3 years ago
- Recycling diverse models☆46Jan 18, 2023Updated 3 years ago
- Open-source code for Generic Grouping Network (GGN, CVPR 2022)☆114Jan 28, 2026Updated last month
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities☆22,030Jan 23, 2026Updated last month
- Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.☆4,371Oct 19, 2025Updated 4 months ago