README.md

metadata

license: cc-by-2.0
language:
  - ko
  - en
pipeline_tag: text2text-generation

사용법

1. 기본 모델

from transformers import AutoModelForSeq2SeqLM,AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained(
    "wisenut-nlp-team/KoT5", 
    use_auth_token=<개인 읽기전용 토큰>
)
model = AutoModelForSeq2SeqLM.from_pretrained(
    "wisenut-nlp-team/KoT5", 
    use_auth_token=<개인 읽기전용 토큰>
)

2. 조정학습 모델

요약(summarization)

from transformers import AutoModelForSeq2SeqLM,AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained(
    "wisenut-nlp-team/KoT5", 
    revision="summarization",
    use_auth_token=<개인 읽기전용 토큰>
)
model = AutoModelForSeq2SeqLM.from_pretrained(
    "wisenut-nlp-team/KoT5", 
    revision="summarization",
    use_auth_token=<개인 읽기전용 토큰>
)

바꿔쓰기(paraphrase generation)

from transformers import AutoModelForSeq2SeqLM,AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained(
    "wisenut-nlp-team/KoT5", 
    revision="paraphrase",
    use_auth_token=<개인 읽기전용 토큰>
)
model = AutoModelForSeq2SeqLM.from_pretrained(
    "wisenut-nlp-team/KoT5", 
    revision="paraphrase",
    use_auth_token=<개인 읽기전용 토큰>
)