BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation

Documenti analoghi

• EfficientQAT: Efficient Quantization-Aware Training for Large Language Models
  di: Chen, Mengzhao, et al.
  Pubblicazione: (2024)
• OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
  di: Shao, Wenqi, et al.
  Pubblicazione: (2023)
• SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models
  di: Lu, Xudong, et al.
  Pubblicazione: (2024)
• PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization
  di: Chen, Mengzhao, et al.
  Pubblicazione: (2024)
• DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model
  di: Zhao, Lirui, et al.
  Pubblicazione: (2024)