Your Transformer Is Secretly Elastic
A retraining-free method turns transformers into elastic models that prune smoothly up to 60% sparsity.
2 stories, newest first · one card per story
A retraining-free method turns transformers into elastic models that prune smoothly up to 60% sparsity.
A retraining-free method makes pretrained transformers elastic, pruning smoothly to 60% sparsity with small accuracy loss.
Today 388 readers · 429 views · 38 reads · all time 109K views