Curia: A Multi-Modal Foundation Model for Radiology Paper • 2509.06830 • Published Sep 8, 2025 • 21
cmarkea/distilcamembert-base-sentiment Text Classification • 68.1M • Updated Oct 26, 2024 • 11.2k • • 39
view post Post 1859 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