Aradhye2002/selective-peft-toolkit

Official implementation of the paper "Step-by-Step Unmasking for Parameter-Efficient Fine-tuning of Large Language Models"

31
/ 100
Emerging

This toolkit helps machine learning engineers and researchers efficiently adapt large language models (LLMs) and other deep learning models for specific tasks without needing to update all millions of their parameters. You input a pre-trained model and your specific dataset, and it outputs a model adapted to your data with significantly fewer updated parameters, making it faster and less resource-intensive. This is ideal for those who need to fine-tune large models on custom datasets with limited computational resources.

No commits in the last 6 months.

Use this if you need to fine-tune large pre-trained models for specific tasks but want to minimize the computational cost and storage requirements by updating only a small, critical subset of parameters.

Not ideal if you have unlimited computational resources and want to perform a full fine-tuning of all model parameters, or if your model is small enough that parameter-efficient techniques offer negligible benefits.

large-language-models model-fine-tuning resource-optimization deep-learning-optimization computer-vision
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

9

Forks

1

Language

Python

License

MIT

Last pushed

Jul 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Aradhye2002/selective-peft-toolkit"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.