A two-parameter Weibull lens on transformer weights — diagnose weight-magnitude distributions (shape k, scale λ) across 7 model families, and explain how λ evolves under AdamW training. Library (npm-weibull-py) + benchmark database + companion code for arXiv:2605.18898 and 2606.19367.
machine-learning deep-learning transformers neural-networks arxiv interpretability weibull-distribution adamw-optimizer training-dynamics model-diagnostics large-language-models llm weight-analysis
-
Updated
Jun 27, 2026 - Python