Downloads · 30 days
39K
1% of all-time downloads
bros-base-uncased
naver-clova-ocr/bros-base-uncased
bros-base-uncased is a feature extraction model from naver-clova-ocr. Use it when you need embeddings to search or compare text. It is set up for transformers.
All-time downloads
2.8M
Public
Repo size
876 MB
Likes
19
Public
Repo makeup
Click a slice to open those files.
.bin438 MB · 100%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- Model type
- bros
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Apr 5, 2022
- SHA
- 0f0e83a5
Model card
From the Hugging Face model README
BROS
GitHub: https://github.com/clovaai/bros
Introduction
BROS (BERT Relying On Spatiality) is a pre-trained language model focusing on text and layout for better key information extraction from documents.<br> Given the OCR results of the document image, which are text and bounding box pairs, it can perform various key information extraction tasks, such as extracting an ordered item list from receipts.<br> For more details, please refer to our paper:
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents<br> Teakgyu Hong, Donghyun Kim, Mingi Ji, Wonseok Hwang, Daehyun Nam, Sungrae Park<br> AAAI 2022 - Main Technical Track
Pre-trained models
| name | # params | Hugging Face - Models |
|---|---|---|
| bros-base-uncased (this) | < 110M | naver-clova-ocr/bros-base-uncased |
| bros-large-uncased | < 340M | naver-clova-ocr/bros-large-uncased |
- Task
- Feature Extraction
- Library
- transformers
- Type
- bros
- Hf Inference
- error
- Created
- Mar 2, 2022
- Updated
- Apr 5, 2022