Downloads · 30 days
7
0% of all-time downloads
KoT5-base
wisenut-nlp-team/KoT5-base
KoT5-base is a text generation model from wisenut-nlp-team. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc-by-2.0.
All-time downloads
18.6K
Public
Repo size
9.8 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.ot1.2 GB · 57%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- cc-by-2.0
- Model type
- t5
- Access
- Public
- Created
- May 24, 2023
- Updated
- May 25, 2023
- SHA
- 785c4e70
Model card
From the Hugging Face model README
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>
)
- Task
- Text Generation
- Library
- transformers
- Type
- t5
- License
- cc-by-2.0
- Languages
- ko, en
- Created
- May 24, 2023
- Updated
- May 25, 2023