microsoft / unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Home Page:https://aka.ms/GeneralAI

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

What's the difference between unilm1.2-base-uncased and unilm2-base-uncased ?

blackskylh opened this issue · comments

I'm using UniLMv2, but I don't know the difference between unilm1.2-base-uncased and unilm2-base-uncased. Is the corpus used for pretrain different?

These two models are described in the paper https://arxiv.org/pdf/2002.12804.pdf .
unilm2 = unilm1.2 + rel_pos (see Table 2, 3 in the paper)