Skip to content
conftrace_

mlp activation

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

parameter dynamics (1) effective rank (1) small language model (1) model scaling (1) training dynamics (1) language model (1) convergence analysis (1) attention mechanism (1)

Papers

Tending Towards Stability: Convergence Challenges in Small Language Models EMNLP 2024