Here is the implementation of our Findings of ACL2024 paper "Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning".
pip install -r requirements.txt
cd peft
pip install -e .
Estimation
bash scripts/estimate.sh
More Efficient Fine-Tuning
bash scripts/train.sh
Vanilla Fine-Tuning
bash scripts/vanilla_train.sh
Thanks for the open source code of EarlyBert, LLM-Adapters, and P-Tuning v2. Some of our codes are based on them.