Picture for Yangfan Bai

Yangfan Bai

SE-MoE: A Scalable and Efficient Mixture-of-Experts Distributed Training and Inference System

Add code
May 20, 2022
Viaarxiv icon

ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation

Add code
Dec 23, 2021
Figure 1 for ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
Figure 2 for ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
Figure 3 for ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
Figure 4 for ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
Viaarxiv icon