Efficient Training of Robust Traditional Chinese LLaMA-1B on a Single Consumer GPU: Continual Pre-training, SFT, and DPO

Documenti analoghi

• LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training
  di: Zhu, Tong, et al.
  Pubblicazione: (2024)
• ECHO-LLaMA: Efficient Caching for High-Performance LLaMA Training
  di: Dialameh, Maryam, et al.
  Pubblicazione: (2025)
• LLaMA Pro: Progressive LLaMA with Block Expansion
  di: Wu, Chengyue, et al.
  Pubblicazione: (2024)
• Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca
  di: Cui, Yiming, et al.
  Pubblicazione: (2023)
• LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training
  di: Qu, Xiaoye, et al.
  Pubblicazione: (2024)