COPAL: Continual Pruning in Large Language Generative Models

arXiv:2405.02347v1 Announce Type: new
Abstract: Adapting pre-trained large language models to different domains in natural language processing requires two key considerations: high computational demands and model's inability to continual adaptation. To simultaneously address both issues, this paper presents COPAL (COntinual Pruning in Adaptive Language settings), an algorithm developed for pruning large language generative models under a continual model adaptation setting. While avoiding resource-heavy finetuning or retraining, our pruning process is guided by the proposed sensitivity analysis. The sensitivity effectively measures …

abstract algorithm arxiv computational continual cs.ai cs.cl cs.lg domains generative generative models key language language models language processing large language large language models natural natural language natural language processing paper processing pruning type