gstoica27 / ZipItLinks
A framework for merging models solving different tasks with different initializations into one multi-task model without any additional training
☆306Updated 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"☆188Updated 2 years ago
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆320Updated 5 months ago
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time☆484Updated last year
- ☆183Updated 11 months ago
- ☆207Updated last year
- Official code for our CVPR'22 paper “Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space”☆251Updated 3 weeks ago
- Learning from synthetic data - code and models☆321Updated last year
- Official implementation of AAAI 2023 paper "Parameter-efficient Model Adaptation for Vision Transformers"☆104Updated 2 years ago
- [NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"☆316Updated last year
- [ICCV2023] Dataset Quantization☆260Updated last year
- PyTorch Implementation of Object Recognition as Next Token Prediction [CVPR'24 Highlight]☆181Updated 4 months ago
- When do we not need larger vision models?☆406Updated 7 months ago
- Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)☆176Updated 3 months ago
- Official implementation of "Describing Differences in Image Sets with Natural Language" (CVPR 2024 Oral)☆121Updated last year
- ☆187Updated last year
- PyTorch code for hierarchical k-means -- a data curation method for self-supervised learning☆189Updated last year
- Repository for the paper: "TiC-CLIP: Continual Training of CLIP Models" ICLR 2024☆104Updated last year
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆360Updated last year
- [ICML 2023] UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers.☆105Updated 8 months ago
- Code release for "Dropout Reduces Underfitting"☆313Updated 2 years ago
- ☆115Updated 2 years ago
- Holds code for our CVPR'23 tutorial: All Things ViTs: Understanding and Interpreting Attention in Vision.☆195Updated 2 years ago
- Official implementation of MAIA, A Multimodal Automated Interpretability Agent☆89Updated 3 months ago
- Code for NOLA, an implementation of "nola: Compressing LoRA using Linear Combination of Random Basis"☆56Updated last year
- Collection of Tools and Papers related to Adapters / Parameter-Efficient Transfer Learning/ Fine-Tuning☆198Updated last year
- ☆190Updated last year
- DataComp: In search of the next generation of multimodal datasets☆743Updated 4 months ago
- Fine-tuning Vision Transformers on various classification datasets☆109Updated last year
- Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"☆53Updated last year
- Editing Models with Task Arithmetic☆500Updated last year