Downloads · 30 days
49
4% of all-time downloads
LIAR-fake-news-roberta-base
Jawaher/LIAR-fake-news-roberta-base
LIAR-fake-news-roberta-base is a fill-mask model from Jawaher. Use it when you need the model to fill a missing word. It is set up for transformers.
A pre-trained Roberta masked language model (MLM) trained on around 12K fake news dataset called LIAR. The perplexity of the original pre-trained Roberta model on the dataset is 5.957 and the perplexity of the adapted…
All-time downloads
1.2K
Public
Repo size
1.7 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.h5655 MB · 57%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Jun 11, 2022
- Updated
- Jun 11, 2022
- SHA
- cb10690d
Try a prompt
Model card
From the Hugging Face model README
A pre-trained Roberta masked language model (MLM) trained on around 12K fake news dataset called LIAR. The perplexity of the original pre-trained Roberta model on the dataset is 5.957 and the perplexity of the adapted model is 3.918.
- Task
- Fill-Mask
- Library
- transformers
- Type
- roberta
- Created
- Jun 11, 2022
- Updated
- Jun 11, 2022