TensorX
返回文献探索

Paper · arXiv 2403.07816

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

Sainbayar Sukhbaatar, Olga Golovneva, Vasu Sharma, Hu Xu, Xi Victoria Lin, Baptiste Rozière, Jacob Kahn, Daniel Li, Wen-tau Yih, Jason Weston, Xian Li

45 upvotesMarch 12, 2024arXiv 预印本
AI 摘要

Branch-Train-MiX (BTX) method enhances Large Language Models by asynchronously training experts in parallel and integrating them using Mixture-of-Expert layers with token-level routing for improved accuracy and efficiency.

Large Language ModelsBranch-Train-MiXBTXseed modelembarrassingly parallelMixture-of-ExpertMoE layerstoken-level routingBranch-Train-Mergesparse upcyclingaccuracy-efficiency tradeoff

Abstract

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.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号
Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM | TensorX