gstoica27 / ZipIt
A framework for merging models solving different tasks with different initializations into one multi-task model without any additional training
☆285Updated 10 months ago
Related projects ⓘ
Alternatives and complementary repositories for ZipIt
- Official code for "TOAST: Transfer Learning via Attention Steering"☆186Updated last year
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time☆429Updated 4 months ago
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆246Updated 6 months ago
- Official code for our CVPR'22 paper “Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space”☆246Updated last year
- When do we not need larger vision models?☆336Updated this week
- ☆170Updated last month
- Learning from synthetic data - code and models☆303Updated 10 months ago
- Object Recognition as Next Token Prediction (CVPR 2024 Highlight)☆161Updated last month
- ☆196Updated last year
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆293Updated 5 months ago
- [NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"☆298Updated 5 months ago
- PyTorch code for hierarchical k-means -- a data curation method for self-supervised learning☆131Updated 5 months ago
- [ICML 2023] UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers.☆99Updated last year
- Collection of Tools and Papers related to Adapters / Parameter-Efficient Transfer Learning/ Fine-Tuning☆176Updated 6 months ago
- Official implementation for the paper "Prompt Pre-Training with Over Twenty-Thousand Classes for Open-Vocabulary Visual Recognition"☆253Updated 6 months ago
- Code release for "Dropout Reduces Underfitting"☆312Updated last year
- [CVPR2024] ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts☆297Updated 4 months ago
- [ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"☆213Updated 3 weeks ago
- Code accompanying the paper "Massive Activations in Large Language Models"☆123Updated 8 months ago
- Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)☆153Updated 11 months ago
- [ICCV2023] Dataset Quantization☆255Updated 10 months ago
- [CVPR 2024] Official implementation of "ViTamin: Designing Scalable Vision Models in the Vision-language Era"☆175Updated 5 months ago
- ☆267Updated last year
- ☆178Updated last year
- Official implementation of "DoRA: Weight-Decomposed Low-Rank Adaptation"☆123Updated 6 months ago
- 1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundatio…☆209Updated 2 months ago
- Official implementation of "Describing Differences in Image Sets with Natural Language" (CVPR 2024 Oral)☆108Updated 7 months ago
- Code for experiments for "ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy"☆96Updated 2 months ago
- Official implementation of AAAI 2023 paper "Parameter-efficient Model Adaptation for Vision Transformers"☆97Updated last year
- This is the official repository for the LENS (Large Language Models Enhanced to See) system.☆351Updated 11 months ago