Downloads · 30 days
6
2% of all-time downloads
news_contrastive_pretrain
yyu/news_contrastive_pretrain
news_contrastive_pretrain is a fill-mask model from yyu. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as mit.
The BERT model pretrained on the news corpus (https://huggingface.co/datasets/yyu/newscorpus). Used in the paper ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval.
All-time downloads
349
Public
Repo size
933 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin438 MB · 88%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Sep 7, 2023
- Updated
- Sep 13, 2023
- SHA
- af208dee
Try a prompt
Model card
From the Hugging Face model README
The BERT model pretrained on the news corpus (https://huggingface.co/datasets/yyu/news_corpus). Used in the paper ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval.
See github: https://github.com/yueyu1030/ReGen and paper: https://arxiv.org/abs/2305.10703 for details.
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- License
- mit
- Created
- Sep 7, 2023
- Updated
- Sep 13, 2023