LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation

Documenti analoghi

• Achieving binary weight and activation for LLMs using Post-Training Quantization
  di: Song, Siqing, et al.
  Pubblicazione: (2025)
• EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation
  di: Zhang, Shu-Hao, et al.
  Pubblicazione: (2026)
• Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models
  di: Xu, Zihuai, et al.
  Pubblicazione: (2025)
• ARB-LLM: Alternating Refined Binarizations for Large Language Models
  di: Li, Zhiteng, et al.
  Pubblicazione: (2024)
• T-LLM: Teaching Large Language Models to Forecast Time Series via Temporal Distillation
  di: Guo, Suhan, et al.
  Pubblicazione: (2026)