Let the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language Models

Documenti analoghi

• DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
  di: Dai, Damai, et al.
  Pubblicazione: (2024)
• ExpertPrompting: Instructing Large Language Models to be Distinguished Experts
  di: Xu, Benfeng, et al.
  Pubblicazione: (2023)
• SciDFM: A Large Language Model with Mixture-of-Experts for Science
  di: Sun, Liangtai, et al.
  Pubblicazione: (2024)
• MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts
  di: Li, Dengchun, et al.
  Pubblicazione: (2024)
• Routing-Aligned Fine-Tuning for Multilingual Downstream Tasks in Mixture-of-Experts Models
  di: Deng, Guanzhi, et al.
  Pubblicazione: (2026)