This is a DeBERTa(V2) model pre-trained on Thai Wikipedia texts. NVIDIA A100-SXM4-40GB took 10 hours 17 minutes for training. You can fine-tune deberta-base-thai for downstream tasks, such as POS-tagging, dependency-parsing, and so on.

How to Use

from transformers import AutoTokenizer,AutoModelForMaskedLM
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/deberta-base-thai")
model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/deberta-base-thai")