david3684 / AdaRank
Official codebase for AdaRank: Adaptive Rank Pruning for Enhanced Model Merging
☆13Updated 3 weeks ago
Alternatives and similar repositories for AdaRank:
Users that are interested in AdaRank are comparing it to the libraries listed below
- Task Singular Vectors: Reducing Task Interference in Model Merging. Merge models avoiding task interference through separable models.☆12Updated 3 weeks ago
- source code for paper "Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models"☆24Updated 10 months ago
- Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]☆43Updated 6 months ago
- ☆13Updated 2 years ago
- ☆27Updated last month
- Deep Learning & Information Bottleneck☆60Updated last year
- AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.☆77Updated 5 months ago
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆57Updated last month
- Official implementation of ORCA proposed in the paper "Cross-Modal Fine-Tuning: Align then Refine"☆71Updated last year
- Benchmark for Natural Temporal Distribution Shift (NeurIPS 2022)☆66Updated 2 years ago
- [NeurIPS 2023 Spotlight] Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training☆34Updated 2 weeks ago
- Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.☆40Updated last year
- Official Pytorch implementation of NeuralWalker☆30Updated 10 months ago
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆101Updated last year
- This is the project for IRM methods☆12Updated 3 years ago
- ☆49Updated last year
- ☆28Updated 3 weeks ago
- virtual node analysis on ogb benchmark dataset☆13Updated 2 years ago
- Official Code for ICLR 2024 Paper: Non-negative Contrastive Learning☆44Updated last year
- Code for paper "Merging Multi-Task Models via Weight-Ensembling Mixture of Experts"☆24Updated 10 months ago
- Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"☆36Updated 2 years ago
- SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining (NeurIPS 2024)☆30Updated 5 months ago
- [ICLR 2023, ICLR DG oral] PAIR, the optimizer and model selection criteria for OOD Generalization☆53Updated last year
- Official implementation of Our NeurIPS 2024 Paper "Boundary Matters: A Bi-Level Active Finetuning Method"☆11Updated 2 months ago
- source code of (quasi-)Givens Orthogonal Fine Tuning integrated to peft lib☆16Updated last month
- Code for "Surgical Fine-Tuning Improves Adaptation to Distribution Shifts" published at ICLR 2023☆29Updated last year
- This is the repository for "Model Merging by Uncertainty-Based Gradient Matching", ICLR 2024.☆27Updated 11 months ago
- ☆18Updated last month
- ☆17Updated last year
- ☆20Updated last month