TOAST approximates full transformer blocks in pretrained models via lightweight closed-form mappings to cut parameters and FLOPs without retraining or finetuning.
Woodfisher: Efficient second-order approximation for neural network compression
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TOAST: Transformer Optimization using Adaptive and Simple Transformations
TOAST approximates full transformer blocks in pretrained models via lightweight closed-form mappings to cut parameters and FLOPs without retraining or finetuning.