This is the repo related to Docker's article on Hybrid AI [0].
> This example demonstrates the MinionS protocol, a groundbreaking approach for cost-efficient collaboration between small on-device models and large cloud models. Based on research from Stanford's Hazy Research lab, MinionS achieves 5.7× cost reduction while maintaining 97.9% of cloud model performance.
1 comment
[ 2.4 ms ] story [ 10.7 ms ] thread> This example demonstrates the MinionS protocol, a groundbreaking approach for cost-efficient collaboration between small on-device models and large cloud models. Based on research from Stanford's Hazy Research lab, MinionS achieves 5.7× cost reduction while maintaining 97.9% of cloud model performance.
[0] https://www.docker.com/blog/hybrid-ai-and-how-it-runs-in-doc...