2 comments

[ 6.3 ms ] story [ 16.9 ms ] thread
ERNIE 4.5, a new family of large-scale multimodal models comprising 10 distinct variants. The model family consist of Mixture-of-Experts (MoE) models with 47B and 3B active parameters, with the largest model having 424B total parameters, as well as a 0.3B dense model.
Anyone trying it out? There's a paper accompanying it