no code implementations • 24 Apr 2024 • Elliot Bolton, Betty Xiong, Vijaytha Muralidharan, Joel Schamroth, Vivek Muralidharan, Christopher D. Manning, Roxana Daneshjou
Large language models, such as GPT-4 and Med-PaLM, have shown impressive performance on clinical tasks; however, they require access to compute, are closed-source, and cannot be deployed on device.