This is a DeBERTa(V2) model pre-trained on Chinese texts (both simplified and traditional) for POS-tagging and dependency-parsing, derived from Erlangshen-DeBERTa-v2-710M-Chinese. Every word is tagged by UPOS (Universal Part-Of-Speech).

or

esupar: Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa/DeBERTa models