Downloads · 30 days
10
2% of all-time downloads
ernie-gram-chinese
swtx/ernie-gram-chinese
ernie-gram-chinese is a feature extraction model from swtx. Use it when you need embeddings to search or compare text. It is set up for transformers.
ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding
All-time downloads
571
Public
Repo size
799 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin400 MB · 100%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jul 8, 2022
- Updated
- Jul 8, 2022
- SHA
- cd16040b
Model card
From the Hugging Face model README
ERNIE-Gram-chinese
Introduction
ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding
More detail: https://arxiv.org/abs/2010.12148
Released Model Info
| Model Name | Language | Model Structure |
|---|---|---|
| ernie-gram-chinese | 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.
- Official PaddlePaddle ERNIE repo: https://github.com/PaddlePaddle/ERNIE
- Pytorch Conversion repo: https://github.com/nghuyong/ERNIE-Pytorch
How to use
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("swtx/ernie-gram-chinese")
model = AutoModel.from_pretrained("swtx/ernie-gram-chinese")
- Task
- Feature Extraction
- Library
- transformers
- Type
- bert
- Created
- Jul 8, 2022
- Updated
- Jul 8, 2022