An iterative hybrid pruning method selects which PEFT modules to keep at each transformer layer, matching or improving fixed PEFT baselines on GLUE at 1% trainable parameters.
Dora: Weight-decomposed low-rank adaptation.ICML 2024,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs
An iterative hybrid pruning method selects which PEFT modules to keep at each transformer layer, matching or improving fixed PEFT baselines on GLUE at 1% trainable parameters.