gstoica27 / ZipItLinks
A framework for merging models solving different tasks with different initializations into one multi-task model without any additional training
☆300Updated last year
Alternatives and similar repositories for ZipIt
Users that are interested in ZipIt are comparing it to the libraries listed below
Sorting:
- Official code for "TOAST: Transfer Learning via Attention Steering"☆189Updated last year
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆299Updated 2 months ago
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time☆470Updated 11 months ago
- ☆203Updated last year
- ☆183Updated last year
- Official code for our CVPR'22 paper “Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space”☆250Updated last year
- ☆181Updated 9 months ago
- Editing Models with Task Arithmetic☆480Updated last year
- PyTorch Implementation of Object Recognition as Next Token Prediction [CVPR 2024 Highlight]☆180Updated last month
- When do we not need larger vision models?☆395Updated 4 months ago
- Learning from synthetic data - code and models☆318Updated last year
- Official implementation of AAAI 2023 paper "Parameter-efficient Model Adaptation for Vision Transformers"☆104Updated last year
- Code release for "Dropout Reduces Underfitting"☆313Updated 2 years ago
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆341Updated last year
- A curated reading list of research in Adaptive Computation, Inference-Time Computation & Mixture of Experts (MoE).☆147Updated 5 months ago
- ☆190Updated last week
- Patching open-vocabulary models by interpolating weights☆91Updated last year
- Collection of Tools and Papers related to Adapters / Parameter-Efficient Transfer Learning/ Fine-Tuning☆192Updated last year
- ☆184Updated last year
- [ICCV2023] Dataset Quantization☆259Updated last year
- [NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"☆315Updated last year
- [ICML 2023] UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers.☆102Updated 5 months ago
- Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)☆167Updated last week
- PyTorch code for hierarchical k-means -- a data curation method for self-supervised learning☆156Updated last year
- DataComp: In search of the next generation of multimodal datasets☆719Updated last month
- Repository for the paper: "TiC-CLIP: Continual Training of CLIP Models".☆102Updated last year
- Code for experiments for "ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy"☆101Updated 9 months ago
- Official implementation for the paper "Prompt Pre-Training with Over Twenty-Thousand Classes for Open-Vocabulary Visual Recognition"☆258Updated last year
- [TPAMI] Searching prompt modules for parameter-efficient transfer learning.☆232Updated last year
- Holds code for our CVPR'23 tutorial: All Things ViTs: Understanding and Interpreting Attention in Vision.☆193Updated 2 years ago