ACE adds activation cosine-similarity and activation-variance terms to the per-weight importance score, and reports better perplexity and lower pruning time than Wanda and RIA on LLaMA, LLaMA-2, and OPT.
Language models are few-shot learners
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning
ACE adds activation cosine-similarity and activation-variance terms to the per-weight importance score, and reports better perplexity and lower pruning time than Wanda and RIA on LLaMA, LLaMA-2, and OPT.