How Much is Too Much? Exploring LoRA Rank Trade-offs for Retaining Knowledge and Domain Robustness

Documenti analoghi

• DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models
  di: Deng, Guanzhi, et al.
  Pubblicazione: (2026)
• LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization
  di: Yen, Jui-Nan, et al.
  Pubblicazione: (2024)
• MiSS: Revisiting the Trade-off in LoRA with an Efficient Shard-Sharing Structure
  di: Kang, Jiale, et al.
  Pubblicazione: (2024)
• Genicious: Contextual Few-shot Prompting for Insights Discovery
  di: Kumar, Vineet, et al.
  Pubblicazione: (2025)
• KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation
  di: Azimi, Rambod, et al.
  Pubblicazione: (2024)