SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model Paper • 2502.02737 • Published 5 days ago • 140
view post Post 1607 Wow, impressive 340B model by nvidia with a nice permissive license! 🚀 The technical report is full of insights and seems to use a different learning rate schedule than cosine, probably a variant of WSD. Hope to get more info on that! 👀 nvidia/nemotron-4-340b-666b7ebaf1b3867caf2f1911 🤗 1 1 + Reply
Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations Paper • 2405.18392 • Published May 28, 2024 • 12