Схожие документы

• LLM-FP4: 4-Bit Floating-Point Quantized Transformers
  по: Liu, Shih-yang, и др.
  Опубликовано: (2023)
• Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection
  по: Huang, Xijie, и др.
  Опубликовано: (2023)
• MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization
  по: Su, Le, и др.
  Опубликовано: (2026)
• Progressive Fine-to-Coarse Reconstruction for Accurate Low-Bit Post-Training Quantization in Vision Transformers
  по: Ding, Rui, и др.
  Опубликовано: (2024)
• MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity
  по: Choi, Kanghyun, и др.
  Опубликовано: (2024)