Spectra 1.1: Scaling Laws and Efficient Inference for Ternary Language Models

Documenti analoghi

• Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale
  di: Kaushal, Ayush, et al.
  Pubblicazione: (2024)
• Graph Partitioning With Limited Moves
  di: Behbahani, Majid, et al.
  Pubblicazione: (2024)
• Small Vocabularies, Big Gains: Pretraining and Tokenization in Time Series Models
  di: Roger, Alexis, et al.
  Pubblicazione: (2025)
• Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting
  di: Riachi, Roland, et al.
  Pubblicazione: (2025)
• Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference
  di: Riemer, Matthew, et al.
  Pubblicazione: (2024)