roymiles / VeLoRALinks
[NeurIPS 2024] VeLoRA : Memory Efficient Training using Rank-1 Sub-Token Projections
☆21Updated 11 months ago
Alternatives and similar repositories for VeLoRA
Users that are interested in VeLoRA are comparing it to the libraries listed below
Sorting:
- Model Merging with SVD to Tie the KnOTS [ICLR 2025]☆68Updated 6 months ago
- Code and benchmark for the paper: "A Practitioner's Guide to Continual Multimodal Pretraining" [NeurIPS'24]☆58Updated 10 months ago
- Code for NOLA, an implementation of "nola: Compressing LoRA using Linear Combination of Random Basis"☆56Updated last year
- Towards Meta-Pruning via Optimal Transport, ICLR 2024 (Spotlight)☆16Updated 10 months ago
- [NeurIPS'24] Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization☆35Updated last year
- ☆21Updated 2 years ago
- This is a PyTorch implementation of the paperViP A Differentially Private Foundation Model for Computer Vision☆36Updated 2 years ago
- This repository is the implementation of the paper Training Free Pretrained Model Merging (CVPR2024).☆30Updated last year
- Implementation for <Orthogonal Over-Parameterized Training> in CVPR'21.☆22Updated 4 years ago
- Metrics for "Beyond neural scaling laws: beating power law scaling via data pruning " (NeurIPS 2022 Outstanding Paper Award)☆57Updated 2 years ago
- ☆26Updated 4 months ago
- SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining (NeurIPS 2024)☆34Updated 11 months ago
- ☆38Updated last year
- Official code for "pi-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation", ICML 2023.☆33Updated 2 years ago
- Code for "Are “Hierarchical” Visual Representations Hierarchical?" in NeurIPS Workshop for Symmetry and Geometry in Neural Representation…☆21Updated last year
- ☆43Updated 11 months ago
- Code for T-MARS data filtering☆35Updated 2 years ago
- ☆19Updated 8 months ago
- ☆32Updated 8 months ago
- [ICLR 2025] Official Pytorch Implementation of "Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN" by Pengxia…☆26Updated 2 months ago
- Switch EMA: A Free Lunch for Better Flatness and Sharpness☆26Updated last year
- Code for paper "Parameter Efficient Multi-task Model Fusion with Partial Linearization"☆22Updated last year
- AdaSplash: Adaptive Sparse Flash Attention (aka Flash Entmax Attention)☆26Updated last week
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆125Updated 3 months ago
- Official Code for ICLR 2024 Paper: Non-negative Contrastive Learning☆45Updated last year
- Official implementation of "Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization"☆80Updated last year
- [NeurIPS'24] Official PyTorch implementation for paper "Knowledge Composition using Task Vectors with Learned Anisotropic Scaling"☆25Updated 7 months ago
- [ICLR 2024 Oral] Improving Convergence and Generalization Using Parameter Symmetries☆29Updated last year
- ☆53Updated 2 years ago
- Test-Time Distribution Normalization For Contrastively Learned Vision-language Models☆27Updated last year