Weight Pair Encoding: Inducing a Smaller Grammar in Neural Network Weights
WeightPE finetunes int8 weights so Re-Pair grammars shrink to 0.38–0.43x of QAT, costing about 1–2 accuracy points.
1 stories, newest first · one card per story
WeightPE finetunes int8 weights so Re-Pair grammars shrink to 0.38–0.43x of QAT, costing about 1–2 accuracy points.
Today 1.2K readers · 1.4K views · 193 reads · all time 203K views