Jacob Woge Nielsen

Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?

2025

Large language models (LLMs) require immense resources for training and inference.Quantization, a technique that reduces the precision of model parameters, offers a promising solution for improving LLM efficiency and sustainability.While post-training quantization methods typically achieve …