EnnengYang / AdaMerging

AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.
https://openreview.net/pdf?id=nZP6NgD3QY
MIT License
40 stars 2 forks source link

code to fine-tune on individual tasks #4

Open sorobedio opened 2 months ago

sorobedio commented 2 months ago

Hello. thank you for your work i am interested in fine-tuning individual task. do you have the code for that. thank you

EnnengYang commented 2 months ago

Hello,

Thank you very much for your attention.

The code to fine-tune individual models can be found at: https://github.com/mlfoundations/task_vectors/blob/main/src/finetune.py

Wish you everything.

Sincerely, Enneng