Olica prunes LLMs without retraining by low-rank decomposing attention-layer matrix products and adding small linear corrections to pruned feed-forward layers, matching or beating retraining-based methods on several benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Olica: Efficient Structured Pruning of Large Language Models without Retraining
Olica prunes LLMs without retraining by low-rank decomposing attention-layer matrix products and adding small linear corrections to pruned feed-forward layers, matching or beating retraining-based methods on several benchmarks.