Views
No views yet




1from transformers import AutoModel, AutoTokenizer
2from syllabletokenizer import SyllableTokenizer
3
4# 모델과 토크나이저 불러오기
5model = AutoModelForMaskedLM.from_pretrained("Trofish/korean_syllable_roberta")
6tokenizer = SyllableTokenizer(vocab_file='vocab.json',**tokenizer_kwargs)
7
8# 텍스트를 토큰으로 변환하고 예측 수행
9inputs = tokenizer("여기에 한국어 텍스트 입력", return_tensors="pt")
10outputs = model(**inputs)@misc{park2021klue,
title={KLUE: Korean Language Understanding Evaluation},
author={Sungjoon Park and Jihyung Moon and Sungdong Kim and Won Ik Cho and Jiyoon Han and Jangwon Park and Chisung Song and Junseong Kim and Yongsook Song and Taehwan Oh and Joohong Lee and Juhyun Oh and Sungwon Lyu and Younghoon Jeong and Inkwon Lee and Sangwoo Seo and Dongjun Lee and Hyunwoo Kim and Myeonghwa Lee and Seongbo Jang and Seungwon Do and Sunkyoung Kim and Kyungtae Lim and Jongwon Lee and Kyumin Park and Jamin Shin and Seonghyun Kim and Lucy Park and Alice Oh and Jungwoo Ha and Kyunghyun Cho},
year={2021},
eprint={2105.09680},
archivePrefix={arXiv},
primaryClass={cs.CL}
}