Branch-Train-MiX：将专家大语言模型混合为混合专家大语言模型
Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
AI总结：
该研究提出名为Branch-Train-MiX（BTX）的大语言模型高效训练方法，通过种子模型分支并行训练多领域专家、整合参数后做MoE微调，实现了更优的准确率与效率权衡。
摘要：
我们研究了让大语言模型（LLMs）具备编码、数学推理和世界知识等多个专业领域能力的高效训练方法。我们的方法名为Branch-Train-MiX（BTX），从一个种子模型出发，将其分支后以易并行的方式训练专家模型，兼具高吞吐量与更低的通信成本。各专家模型异步训练完成后，BTX将它们的前馈参数整合为混合专家（MoE）层的专家参数，对其余参数取平均，随后进入MoE微调阶段以学习token级路由。BTX涵盖了两种特殊情况：无需MoE微调阶段学习路由的Branch-Train-Merge方法，以及省略异步训练专家阶段的稀疏上扩方法。与其他替代方法相比，BTX实现了最优的准确率-效率权衡。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
