DenoiseRotator: Enhance Pruning Robustness for LLMs via Importance Concentration

Documenti analoghi

• One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models
  di: Shao, Hang, et al.
  Pubblicazione: (2023)
• MoreauPruner: Robust Pruning of Large Language Models against Weight Perturbations
  di: Wang, Zixiao, et al.
  Pubblicazione: (2024)
• CLAQ: Pushing the Limits of Low-Bit Post-Training Quantization for LLMs
  di: Wang, Haoyu, et al.
  Pubblicazione: (2024)
• Enhancing Efficiency and Exploration in Reinforcement Learning for LLMs
  di: Liao, Mengqi, et al.
  Pubblicazione: (2025)
• On Importance of Pruning and Distillation for Efficient Low Resource NLP
  di: Mirashi, Aishwarya, et al.
  Pubblicazione: (2024)