MinionS (Cost-efficient Collaboration Between On-device and Cloud
Language Models) - a new protocol to achieve proprietary cloud LLM performance to a fraction of the costs by integrating your local PC with an open source LLM in the loop.
All rights w/ authors:
"Minions: Cost-efficient Collaboration Between On-device and Cloud
Language Models"
Avanika Narayan, Dan Biderman, Sabri Eyuboglu, Avner May,
Scott Linderman, James Zou, Christopher R´e
Department of Computer Science, Stanford University
Department of Statistics, Stanford University
Wu Tsai Neurosciences Institute, Stanford University
Department of Biomedical Data Science, Stanford University
Together AI