This is a DeBERTa(V2) model pre-trained on Thai Wikipedia texts for POS-tagging and dependency-parsing (using goeswith for subwords), derived from deberta-base-thai.
from transformers import pipeline
nlp=pipeline("universal-dependencies","KoichiYasuoka/deberta-base-thai-ud-goeswith",trust_remote_code=True,aggregation_strategy="simple")
print(nlp("หลายหัวดีกว่าหัวเดียว"))
KoichiYasuoka/deberta-base-thai