Poodle: Seamlessly Scaling Down Large Language Models with Just-in-Time Model Replacement

Documenti analoghi

• Learning from Uncertain Data: From Possible Worlds to Possible Models
  di: Zhu, Jiongli, et al.
  Pubblicazione: (2024)
• An Empirical Evaluation of Serverless Cloud Infrastructure for Large-Scale Data Processing
  di: Bodner, Thomas, et al.
  Pubblicazione: (2025)
• SMART: Automatically Scaling Down Language Models with Accuracy Guarantees for Reduced Processing Fees
  di: Jo, Saehan, et al.
  Pubblicazione: (2024)
• SEED: Domain-Specific Data Curation With Large Language Models
  di: Chen, Zui, et al.
  Pubblicazione: (2023)
• Magneto: Combining Small and Large Language Models for Schema Matching
  di: Liu, Yurong, et al.
  Pubblicazione: (2024)