Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM

Sainbayar Sukhbaatar, Olga Golovneva, Vasu Sharma, Hu Xu, Xi V Lin, Baptiste Roziere, Jacob Kahn, Shang-Wen Li, Scott Yih, JASON WESTON, Xian Li

Conference On Language Models 1 pre-proceedings (COLM 2024) Conference

BibTeX download is not available in the pre-proceeding

We investigate efficient methods for training Large Language Models (LLMs) to possess capabilities in multiple specialized domains, such as coding, math reasoning and world knowledge. Our method, named Branch-Train-MiX (BTX), starts from a seed model, which is branched to train experts in embarrassingly parallel fashion with high throughput and reduced communication cost. After individual experts are asynchronously trained, BTX brings together their feedforward parameters as experts in Mixture-of-Expert (MoE) layers and averages the remaining parameters, followed by an MoE-finetuning stage to learn token-level routing. BTX generalizes two special cases, the Branch-Train-Merge method, which does not have the MoE finetuning stage to learn routing, and sparse upcycling, which omits the stage of training experts asynchronously. Compared to alternative approaches, BTX achieves the best accuracy-efficiency tradeoff.