arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.19173cs.CLcs.AI
收藏

HM3:异构多类模型合并

HM3: Heterogeneous Multi-Class Model Merging

Datarobot(达特罗博特)

Stefan Hackmann

AI总结:

本文提出HM3方法,通过免训练方式合并异构多类防护模型,在提升部分模型F1分数的同时将推理时间最多降低44%,并探讨了自合并对任务向量密度的影响。

摘要:

基础语言模型部署通常包含辅助的防护栏模型,用于过滤或分类文本、检测越狱尝试、有偏见或有毒输出,或确保主题一致性。这些额外模型增加了模型推理的复杂性和成本,尤其是其中许多本身也是大型语言模型。为了解决这一问题,我们探索了免训练的模型合并技术,将这些模型整合为一个单一的多功能模型。我们提出异构多类模型合并(HM3),作为一种合并具有异构标签空间的多类分类器的简单技术。与LoRA等参数高效微调技术不同,后者需要大量训练并在推理过程中增加复杂性,近期进展允许以免训练的方式合并模型。我们报告了合并基于BERT的防护模型的有前景结果,其中一些模型取得了高于源模型的平均F1分数,同时将推理时间最多减少了44%。我们引入自合并来评估任务向量密度降低的影响,发现表现较差的有毒言论分类器从自合并中受益,而表现较高的分类器则没有,这引发了关于使用任务向量缩减进行模型调优的问题。

英文摘要:

Foundation language model deployments often include auxiliary guard-rail models to filter or classify text, detecting jailbreak attempts, biased or toxic output, or ensuring topic adherence. These additional models increase the complexity and cost of model inference, especially since many are also large language models. To address this issue, we explore training-free model merging techniques to consolidate these models into a single, multi-functional model. We propose Heterogeneous Multi-Class Model Merging (HM3) as a simple technique for merging multi-class classifiers with heterogeneous label spaces. Unlike parameter-efficient fine-tuning techniques like LoRA, which require extensive training and add complexity during inference, recent advancements allow models to be merged in a training-free manner. We report promising results for merging BERT-based guard models, some of which attain an average F1-score higher than the source models while reducing the inference time by up to 44%. We introduce self-merging to assess the impact of reduced task-vector density, finding that the more poorly performing hate speech classifier benefits from self-merging while higher-performing classifiers do not, which raises questions about using task vector reduction for model tuning.

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。

↑