Downloads · 30 days
18
0% of all-time downloads
theSOL1/kogrammar-distil
kogrammar-distil is a machine learning model from theSOL1. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
Dataset: 국립국어원 맞춤법 교정 말뭉치 <br <br Backbone Model: - kobart-base-v2
Downloads · 30 days
18
0% of all-time downloads
All-time downloads
5.5K
Public
Repo size
764 MB
Likes
0
Public
Click a slice to open those files.
.bin382 MB · 100%
From the Hugging Face model README
Dataset: 국립국어원 맞춤법 교정 말뭉치 <br> <br> Backbone Model:
Contributors:
GitHub Repo:
전체 데이터셋 중 약 67.5%를 학습데이터로 활용하여 학습함. <br> SFT Distillation을 이용해 kogrammar-base 모델의 Decoder Layer를 6개에서 3개로 줄여 다시 학습시킴.
| BLEU-2 | ROUGE-2 F1 |
|---|---|
| 77.8 % | 55.0 % |