At equal small sizes, encoder-decoder language models are faster on edge hardware and, after distillation from a larger decoder-only teacher, match or beat decoder-only models on several benchmarks.
Ac- cessed: 2024-12-03
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
-
Return of the Encoder: Maximizing Parameter Efficiency for SLMs
At equal small sizes, encoder-decoder language models are faster on edge hardware and, after distillation from a larger decoder-only teacher, match or beat decoder-only models on several benchmarks.