HFT: Half Fine-Tuning for Large Language Models

Documenti analoghi

• Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging
  di: Hui, Tingfeng, et al.
  Pubblicazione: (2024)
• Advantageous Parameter Expansion Training Makes Better Large Language Models
  di: Gu, Naibin, et al.
  Pubblicazione: (2025)
• Phased Instruction Fine-Tuning for Large Language Models
  di: Pang, Wei, et al.
  Pubblicazione: (2024)
• Tool-Augmented Reward Modeling
  di: Li, Lei, et al.
  Pubblicazione: (2023)
• Curiosity-Driven Reinforcement Learning from Human Feedback
  di: Sun, Haoran, et al.
  Pubblicazione: (2025)