Downloads · 30 days
472
1% of all-time downloads
nghuyong/ernie-health-zh
ernie-health-zh is a feature extraction model from nghuyong. Use it when you need embeddings to search or compare text. It is set up for transformers.
ERNIE-health is a Chinese biomedical language model pre-trained from in-domain text of de-identified online doctor-patient dialogues, electronic medical records, and textbooks.
Downloads · 30 days
472
1% of all-time downloads
All-time downloads
41.4K
Public
Repo size
1.6 GB
Likes
15
Public
Click a slice to open those files.
.bin411 MB · 100%
From the Hugging Face model README
ERNIE-health is a Chinese biomedical language model pre-trained from in-domain text of de-identified online doctor-patient dialogues, electronic medical records, and textbooks.
More detail: https://github.com/PaddlePaddle/PaddleNLP/blob/develop/model_zoo/ernie-health/ https://arxiv.org/pdf/2110.07244.pdf
| Model Name | Language | Model Structure |
|---|---|---|
| ernie-health-zh | Chinese | Layer:12, Hidden:768, Heads:12 |
This released pytorch model is converted from the officially released PaddlePaddle ERNIE model and a series of experiments have been conducted to check the accuracy of the conversion.
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("nghuyong/ernie-health-zh")
model = AutoModel.from_pretrained("nghuyong/ernie-health-zh")
@article{wang2021building,
title={Building Chinese Biomedical Language Models via Multi-Level Text Discrimination},
author={Wang, Quan and Dai, Songtai and Xu, Benfeng and Lyu, Yajuan and Zhu, Yong and Wu, Hua and Wang, Haifeng},
journal={arXiv preprint arXiv:2110.07244},
year={2021}
}