Downloads ยท 30 days
4.4K
4% of all-time downloads
lighthouse/mdeberta-v3-base-kor-further
mdeberta-v3-base-kor-further is a machine learning model from lighthouse. 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.
๐ก ์๋ ํ๋ก์ ํธ๋ KPMG Lighthouse Korea์์ ์งํํ์์ต๋๋ค. KPMG Lighthouse Korea์์๋, Financial area์ ๋ค์ํ ๋ฌธ์ ๋ค์ ํด๊ฒฐํ๊ธฐ ์ํด Edge Technology์ NLP/Vision AI๋ฅผ ๋ชจ๋ธ๋งํ๊ณ ์์ต๋๋ค. https://kpmgkr.notion.site/
Downloads ยท 30 days
4.4K
4% of all-time downloads
All-time downloads
124K
Public
Repo size
2.2 GB
Likes
19
Public
Click a slice to open those files.
.bin559 MB ยท 99%
From the Hugging Face model README
๐ก ์๋ ํ๋ก์ ํธ๋ย KPMG Lighthouse Korea์์ ์งํํ์์ต๋๋ค.
KPMG Lighthouse Korea์์๋, Financial area์ ๋ค์ํ ๋ฌธ์ ๋ค์ ํด๊ฒฐํ๊ธฐ ์ํด Edge Technology์ NLP/Vision AI๋ฅผ ๋ชจ๋ธ๋งํ๊ณ ์์ต๋๋ค. https://kpmgkr.notion.site/
Disentangled Attention + Enhanced Mask Decoder ๋ฅผ ์ ์ฉํ์ฌ ๋จ์ด์ positional information์ ํจ๊ณผ์ ์ผ๋ก ํ์ตํฉ๋๋ค. ์ด์ ๊ฐ์ ์์ด๋์ด๋ฅผ ํตํด, ๊ธฐ์กด์ BERT, RoBERTa์์ ์ฌ์ฉํ๋ absolute position embedding๊ณผ๋ ๋ฌ๋ฆฌ DeBERTa๋ ๋จ์ด์ ์๋์ ์ธ ์์น ์ ๋ณด๋ฅผ ํ์ต ๊ฐ๋ฅํ ๋ฒกํฐ๋ก ํํํ์ฌ ๋ชจ๋ธ์ ํ์ตํ๊ฒ ๋ฉ๋๋ค. ๊ฒฐ๊ณผ์ ์ผ๋ก, BERT, RoBERTA ์ ๋น๊ตํ์ ๋ ๋ ์ค์ํ ์ฑ๋ฅ์ ๋ณด์ฌ์ฃผ์์ต๋๋ค.mDeBERTa-v3-base-kor-further ๋ microsoft ๊ฐ ๋ฐํํ mDeBERTa-v3-base ๋ฅผ ์ฝ 40GB์ ํ๊ตญ์ด ๋ฐ์ดํฐ์ ๋ํด์ ์ถ๊ฐ์ ์ธ ์ฌ์ ํ์ต์ ์งํํ ์ธ์ด ๋ชจ๋ธ์
๋๋ค.pip install transformers
pip install sentencepiece
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("lighthouse/mdeberta-v3-base-kor-further") # DebertaV2ForModel
tokenizer = AutoTokenizer.from_pretrained("lighthouse/mdeberta-v3-base-kor-further") # DebertaV2Tokenizer (SentencePiece)
๋ชจ๋ธ์ ์ํคํ
์ฒ๋ ๊ธฐ์กด microsoft์์ ๋ฐํํ mdeberta-v3-base์ ๋์ผํ ๊ตฌ์กฐ์
๋๋ค.
| Vocabulary(K) | Backbone Parameters(M) | Hidden Size | Layers | Note | |
|---|---|---|---|---|---|
| mdeberta-v3-base-kor-further (mdeberta-v3-base์ ๋์ผ) | 250 | 86 | 768 | 12 | 250K new SPM vocab |
mDeBERTa-v3-base-kor-further ๋ microsoft/mDeBERTa-v3-base ๋ฅผ ์ฝ 40GB์ ํ๊ตญ์ด ๋ฐ์ดํฐ์ ๋ํด์ MLM Task๋ฅผ ์ ์ฉํ์ฌ ์ถ๊ฐ์ ์ธ ์ฌ์ ํ์ต์ ์งํํ์์ต๋๋ค.
| Max length | Learning Rate | Batch Size | Train Steps | Warm-up Steps | |
|---|---|---|---|---|---|
| mdeberta-v3-base-kor-further | 512 | 2e-5 | 8 | 5M | 50k |
| Model | Size | NSMC(acc) | Naver NER(F1) | PAWS (acc) | KorNLI (acc) | KorSTS (spearman) | Question Pair (acc) | KorQuaD (Dev) (EM/F1) | Korean-Hate-Speech (Dev) (F1) |
|---|---|---|---|---|---|---|---|---|---|
| XLM-Roberta-Base | 1.03G | 89.03 | 86.65 | 82.80 | 80.23 | 78.45 | 93.80 | 64.70 / 88.94 | 64.06 |
| mdeberta-base | 534M | 90.01 | 87.43 | 85.55 | 80.41 | 82.65 | 94.06 | 65.48 / 89.74 | 62.91 |
| mdeberta-base-kor-further (Ours) | 534M | 90.52 | 87.87 | 85.85 | 80.65 | 81.90 | 94.98 | 66.07 / 90.35 | 68.16 |
@misc{he2021debertav3,
title={DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing},
author={Pengcheng He and Jianfeng Gao and Weizhu Chen},
year={2021},
eprint={2111.09543},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
@inproceedings{
he2021deberta,
title={DEBERTA: DECODING-ENHANCED BERT WITH DISENTANGLED ATTENTION},
author={Pengcheng He and Xiaodong Liu and Jianfeng Gao and Weizhu Chen},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://openreview.net/forum?id=XPZIaotutsD}
}