TextPruner: A Model Pruning Toolkit for Pre-Trained Language Models
This toolkit addresses resource limitations for NLP practitioners, but it is incremental as it builds on existing pruning methods.
The authors tackled the high computational demands of pre-trained language models by introducing TextPruner, a toolkit for model pruning that reduces model size without re-training, as demonstrated in experiments on several NLP tasks.
Pre-trained language models have been prevailed in natural language processing and become the backbones of many NLP tasks, but the demands for computational resources have limited their applications. In this paper, we introduce TextPruner, an open-source model pruning toolkit designed for pre-trained language models, targeting fast and easy model compression. TextPruner offers structured post-training pruning methods, including vocabulary pruning and transformer pruning, and can be applied to various models and tasks. We also propose a self-supervised pruning method that can be applied without the labeled data. Our experiments with several NLP tasks demonstrate the ability of TextPruner to reduce the model size without re-training the model.