KoichiYasuoka's picture
base_model
adca5b0
|
raw
history blame
1.22 kB
metadata
language:
  - zh
tags:
  - chinese
  - token-classification
  - pos
  - dependency-parsing
base_model: IDEA-CCNL/Erlangshen-DeBERTa-v2-710M-Chinese
datasets:
  - universal_dependencies
license: apache-2.0
pipeline_tag: token-classification

deberta-xlarge-chinese-erlangshen-upos

Model Description

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).

How to Use

from transformers import AutoTokenizer,AutoModelForTokenClassification
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/deberta-xlarge-chinese-erlangshen-upos")
model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/deberta-xlarge-chinese-erlangshen-upos")

or

import esupar
nlp=esupar.load("KoichiYasuoka/deberta-xlarge-chinese-erlangshen-upos")

See Also

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