D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models

Documenti analoghi

• DDK: Distilling Domain Knowledge for Efficient Large Language Models
  di: Liu, Jiaheng, et al.
  Pubblicazione: (2024)
• E^2-LLM: Efficient and Extreme Length Extension of Large Language Models
  di: Liu, Jiaheng, et al.
  Pubblicazione: (2024)
• FALCON: Pinpointing and Mitigating Stragglers for Large-Scale Hybrid-Parallel Training
  di: Wu, Tianyuan, et al.
  Pubblicazione: (2024)
• An introduction to univalent function theory and the Bieberbach conjecture
  di: Qu, Jiakai
  Pubblicazione: (2024)
• ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models
  di: Wu, Yanan, et al.
  Pubblicazione: (2024)