Instructions to use eunjin/koMHBERT-kcbert-based-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eunjin/koMHBERT-kcbert-based-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="eunjin/koMHBERT-kcbert-based-v1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("eunjin/koMHBERT-kcbert-based-v1") model = AutoModel.from_pretrained("eunjin/koMHBERT-kcbert-based-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
upload flax model
3022b64 -
allow flax
825321c
-
Create README.md
d5a842a -
Create README.mdโ
korean Mental Health BERT kcBERT๋ฅผ ์๋์ dataset์ผ๋ก MLM fine-tuiningํ Bert Model์ ๋๋ค. ์ ์ ๊ฑด๊ฐ ๋ฌธ์ ํด๊ฒฐ์ ๋์์ด ๋ ๋งํ ๋ฐ์ดํฐ์ ์ด๋ผ๊ณ ํ๋จํ์ฌ domain-adaptationํ์๊ณ , ํฅํ ์ ์ ๊ฑด๊ฐ ๊ด๋ จ ๊ฐ์ ๋ฐ ์ํ classification ๋ฐ ๊ทธ์ ๋ฐ๋ฅธ chatbot ๊ตฌํ์ ์ฌ์ฉํ ์ ์์ต๋๋ค. ์ดํ ๊ณต๊ฐ๋ ์์ ์ธ ๋ ํฐ ๊ท๋ชจ์ ๋ฐ์ดํฐ์ ๊น์ง Daptํ ์์ ์ ๋๋ค. datasets from AIhub ์ฐ๋์ค ๋ํ ์คํฌ๋ฆฝํธ ๋ฐ์ดํฐ์ 1 & 2 (์ค๋ณต ์ ๊ฑฐ ์ฝ 2๋ง9์ฒ๊ฐ) @inproceedings{lee2020kcbert, title={KcBERT: Korean Comments BERT}, author={Lee, Junbum}, booktitle={Proceedings of the 32nd Annual Conference on Human and Cognitive Language Technology}, pages={437--440}, year={2020} }b563374 -
kcbert based version1
2343c90 -
initial commit
bd15b8d