https://github.com/kyegomez/evovlm-jp

Plug in & Play Pytorch Implementation of the paper: "Evolutionary Optimization of Model Merging Recipes" by Sakana AI
https://github.com/kyegomez/evovlm-jp

Last synced: 5 months ago
JSON representation

Plug in & Play Pytorch Implementation of the paper: "Evolutionary Optimization of Model Merging Recipes" by Sakana AI

• Host: GitHub
• URL: https://github.com/kyegomez/evovlm-jp
• Owner: kyegomez
• License: mit
• Created: 2024-03-21T06:17:16.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-11-11T01:46:06.000Z (11 months ago)
• Last Synced: 2025-04-19T20:17:12.839Z (6 months ago)
• Language: Python
• Size: 2.16 MB
• Stars: 30
• Watchers: 6
• Forks: 1
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE

Awesome Lists containing this project

README

          
[![Multi-Modality](agorabanner.png)](https://discord.gg/qUtxnK2NMf)

# EVO

Plug in & Play Pytorch Implementation of the paper: "Evolutionary Optimization of Model Merging Recipes" by Sakana AI! This repository will host all merge methods presented in the paper such as DARE, TaskArithmetic, TIESMerging, and the evolutionary algorithm they use. Also, I attempt to implement their future work to create swarms of models using merge methods for various real-world verticals!

## Todo

- [ ] Implement the evolutionary algorithm

- [ ] Make it plug in and play

# License

MIT