Merging aligned feed-forward sublayers into tied weights can remove over a third of a Transformer's feed-forward parameters with only small performance losses, after a short fine-tuning.
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
-
Merging Feed-Forward Sublayers for Compressed Transformers
Merging aligned feed-forward sublayers into tied weights can remove over a third of a Transformer's feed-forward parameters with only small performance losses, after a short fine-tuning.