Scalable Data Ablation Approximations for Language Models through Modular Training and Merging

Documenti analoghi

• Just CHOP: Embarrassingly Simple LLM Compression
  di: Jha, Ananya Harsh, et al.
  Pubblicazione: (2023)
• TRAM: Bridging Trust Regions and Sharpness Aware Minimization
  di: Sherborne, Tom, et al.
  Pubblicazione: (2023)
• Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging
  di: Morrison, Jacob, et al.
  Pubblicazione: (2024)
• Holistically Evaluating the Environmental Impact of Creating Language Models
  di: Morrison, Jacob, et al.
  Pubblicazione: (2025)
• AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters
  di: Lucy, Li, et al.
  Pubblicazione: (2024)