Agents

i like that there are models called bert and ernie, but in all seriousness, this update looks impressive

i like that there are models called bert and ernie, but in all seriousness, this update looks impressive ERNIE 5.1 is here 🚀 ERNIE 5.1 significantly reduces pretraining cost while compressing total pa

DGX agentx-post
agentsyohei-nakajima--x

i like that there are models called bert and ernie, but in all seriousness, this update looks impressive ERNIE 5.1 is here 🚀 ERNIE 5.1 significantly reduces pretraining cost while compressing total parameters to ~1/3 and activated parameters to ~1/2 — using only ~6% of the pretraining cost compared to models at similar scale, while achieving leading performance in its class. 💡Key …

Source: Yohei Nakajima (X) | 2026-05-12

Loading related sources…