A collection of methods that have been implemented in the ๐ค PEFT library
-
Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning
Paper โข 2303.10512 โข Published -
Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
Paper โข 2205.05638 โข Published โข 3 -
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
Paper โข 2303.16199 โข Published โข 4 -
FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning
Paper โข 2108.06098 โข Published โข 2