SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters

Documenti analoghi

• You Only Use Reactive Attention Slice For Long Context Retrieval
  di: Soh, Yun Joon, et al.
  Pubblicazione: (2024)
• Variance Alignment Score: A Simple But Tough-to-Beat Data Selection Method for Multimodal Contrastive Learning
  di: Wang, Yiping, et al.
  Pubblicazione: (2024)
• JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention
  di: Tian, Yuandong, et al.
  Pubblicazione: (2023)
• Multi-modal Learning for WebAssembly Reverse Engineering
  di: Huang, Hanxian, et al.
  Pubblicazione: (2024)
• Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking
  di: Tian, Yuandong
  Pubblicazione: (2025)