Hugging Face's logo

yongsun-yoon
/
koenbert-base

Feature Extraction
Transformers
PyTorch
Korean
bert
text-embeddings-inference
Model card Files Community
1

koenbert-base

졜근 λ‹€μ–‘ν•œ ν•œκ΅­μ–΄ μ–Έμ–΄ λͺ¨λΈλ“€μ΄ 개발 및 곡유되고 μžˆμŠ΅λ‹ˆλ‹€. ν•˜μ§€λ§Œ μ΄λŸ¬ν•œ λͺ¨λΈλ“€μ€ ν•œκ΅­μ–΄λ§Œ μ§€μ›ν•˜κΈ° λ•Œλ¬Έμ— Dialog system, Information retrieval λ“± λ‹€μ–‘ν•œ λ„λ©”μΈμ—μ„œ μ œμž‘λ˜λŠ” μ˜μ–΄ 데이터λ₯Ό ν™œμš©ν•˜κΈ° μ–΄λ ΅λ‹€λŠ” ν•œκ³„μ μ΄ μžˆμŠ΅λ‹ˆλ‹€. Multilingual λͺ¨λΈμ˜ 경우 μ§€μ›ν•˜λŠ” μ–Έμ–΄μ˜ μˆ˜κ°€ λ§Žμ•„ λͺ¨λΈ 크기가 크고 ν•œκ΅­μ–΄ μ„±λŠ₯이 λ–¨μ–΄μ§„λ‹€λŠ” 단점이 μžˆμŠ΅λ‹ˆλ‹€. μ΄λŸ¬ν•œ ν•œκ³„μ μ„ ν•΄μ†Œν•˜κ³  ν•œκ΅­μ–΄ λͺ¨λΈμ˜ ν™œμš©λ„λ₯Ό 높이기 μœ„ν•΄ ν•œκ΅­μ–΄ μ–Έμ–΄ λͺ¨λΈμ— μ˜μ–΄λ₯Ό ν•™μŠ΅ν•˜λŠ” ν”„λ‘œμ νŠΈλ₯Ό μ§„ν–‰ν•˜κ³  μžˆμŠ΅λ‹ˆλ‹€. λͺ¨λΈμ— λŒ€ν•œ μžμ„Έν•œ μ •λ³΄λŠ” Github repoμ—μ„œ ν™•μΈν•΄μ£Όμ„Έμš”.

μ‹€ν–‰ 

from transfomers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained('respect5716/koen-bert-base')
model = AutoModel.from_pretrained('respect5716/koen-bert-base')
Downloads last month
18
Inference Providers NEW
Feature Extraction
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support