Llama-3.1-Nemotron-70B Collection SOTA models on Arena Hard and RewardBench as of 1 Oct 2024. • 6 items • Updated Oct 15 • 139
view article Article Illustrating Reinforcement Learning from Human Feedback (RLHF) Dec 9, 2022 • 99
DBRX Collection DBRX is a mixture-of-experts (MoE) large language model trained from scratch by Databricks. • 3 items • Updated Mar 27 • 91