AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation Paper • 2503.19693 • Published 29 days ago • 75
Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics Paper • 2410.21272 • Published Oct 28, 2024 • 2
Running 2.5k 2.5k The Ultra-Scale Playbook 🌌 The ultimate guide to training LLM on large GPU Clusters
SinFusion: Training Diffusion Models on a Single Image or Video Paper • 2211.11743 • Published Nov 21, 2022