All Language Models Large and Small

arXiv:2402.12061v1 Announce Type: new
Abstract: Many leading language models (LMs) use high-intensity computational resources both during training and execution. This poses the challenge of lowering resource costs for deployment and faster execution of decision-making tasks among others. We introduce a novel plug-and-play LM framework named Language Optimising Network Distribution (LONDI) framework. LONDI learns to selectively employ large LMs only where complex decision-making and reasoning are required while using low-resource LMs everywhere else. LONDI consists of a system of two (off-)policy …

abstract arxiv challenge computational costs cs.ai cs.cl cs.lg decision deployment distribution faster framework intensity language language models lms making network novel resources small tasks training type