MediSwift: Efficient Sparse Pre-trained Biomedical Language Models
Vithursan Thangarasa, Mahmoud Ahmed Salem, Shreyas Saxena, Chen-Yu Leong, Joel Hestness, Sean Lie · 2024
Large language models (LLMs) are typically trained on general source data for various domains, but a recent surge in domain-specific LLMs has shown their potential to outperform general-purpose models in domain-specific tasks (e.g., biomedicine).Although domainspecific pre-training enhances efficiency and leads to smaller models, the computational costs of training these LLMs remain high, posing budgeting challenges.We introduce MediSwift, a suite of biomedical LMs that leverage sparse pre-training on domain-specific biomedical text data.By inducing up to 75% weight sparsity during the pre-training phase, MediSwift achieves a 2-2.5x reduction in training FLOPs.Notably, all sparse pre-training was performed on the Cerebras CS-2 system, which is specifically designed to realize the acceleration benefits from unstructured weight sparsity, thereby significantly enhancing the efficiency of the MediSwift models.Through subsequent dense fine-tuning and strategic soft prompting, MediSwift models outperform existing LLMs up to 7B parameters on biomedical tasks, setting new benchmarks w.r.t efficiency-accuracy on tasks such as PubMedQA.Our results show that sparse pre-training, along with dense finetuning and soft prompting, offers an effective method for creating high-performing, computationally efficient models in specialized domains.