Seung-Moo Yang's repositories
anomaly-detection-resources
Anomaly detection related books, papers, videos, and toolboxes
attention_sinks
Extend existing LLMs way beyond the original training length with constant memory usage, and without retraining
biobert
BioBERT: a pre-trained biomedical language representation model
biobert-pytorch
PyTorch Implementation of BioBERT
CounselGPT
ํ๊ตญ์ด ์ฌ๋ฆฌ ์๋ด ๋ฐ์ดํฐ์
FinBERT-QA
Financial Domain Question Answering with pre-trained BERT Language Model
JEN-1-pytorch
Unofficial implementation JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models(https://arxiv.org/abs/2308.04729)
KcBERT
๐ค Pretrained BERT model & WordPiece tokenizer trained on Korean Comments ํ๊ตญ์ด ๋๊ธ๋ก ํ๋ฆฌํธ๋ ์ด๋ํ BERT ๋ชจ๋ธ
KcELECTRA
๐ค Korean Comments ELECTRA: ํ๊ตญ์ด ๋๊ธ๋ก ํ์ตํ ELECTRA ๋ชจ๋ธ
ko-prfrdr
Utils for Korean proofreader
korean-hate-speech-koelectra
Bias, Hate classification with KoELECTRA ๐ฟ
LegalQA
Korean LegalQA using SentenceKoBART
lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
MASKER
MASKER: Masked Keyword Regularization for Reliable Text Classification (AAAI 2021)
my-alpaca
Try original alpaca. The multi-turn version is at [multi-turn-alpaca](https://github.com/l294265421/multi-turn-alpaca) and the version further trained with RLHF (Reinforcement Learning with Human Feedback) is at [alpaca-rlhf](https://github.com/l294265421/alpaca-rlhf).
oslo
OSLO: Open Source framework for Large-scale model Optimization
PyKoSpacing
Automatic Korean word spacing with Python
sentiment-analysis-streamlit
Using Python and Streamlit to build beautiful and interactive dashboards and web apps. Load, explore, visualize and interact with data, and generate dashboards
transformers
๐ค Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.