Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]
-
Updated
Oct 25, 2024 - Python
#
task-arithmetic
Here are 5 public repositories matching this topic...
Official PyTorch implementation for NeurIPS'24 paper "Knowledge Composition using Task Vectors with Learned Anisotropic Scaling"
peft
few-shot-learning
pytorch-implementation
test-time-adaptation
parameter-efficient-fine-tuning
task-arithmetic
neurips-2024
-
Updated
Nov 7, 2024 - Python
-
Updated
Oct 16, 2024 - Mojo
SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery. Arxiv, 2024.
-
Updated
Oct 21, 2024 - Python
This repository contain a project which goal is to find new parameter efficient fine tuning framework in order to improve performance of Deep Artificial Neural Network onto "out of distribution" data (OOD). In this specific case you can find Multi-task Learning problem.
transfer-learning
fine-tuning
mobilenetv2
parameter-efficient-fine-tuning
task-arithmetic
ada-merging
-
Updated
Jul 7, 2024 - Jupyter Notebook
Improve this page
Add a description, image, and links to the task-arithmetic topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the task-arithmetic topic, visit your repo's landing page and select "manage topics."