Downloads · 30 days
8
0% of all-time downloads
Mixed-Distil-BERT
md-nishat-008/Mixed-Distil-BERT
Mixed-Distil-BERT is a fill-mask model from md-nishat-008. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as apache-2.0.
The model is pretrained on the OSCAR dataset for Bangla, English and Hindi. And further pre-trained on 560k code-mixed data (Bangla-English-Hindi). The base model is Distil-BERT and the intended use for this model is…
All-time downloads
1.8K
Public
Repo size
804 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin268 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Sep 17, 2023
- Updated
- Sep 26, 2023
- SHA
- 1990cf6f
Try a prompt
Model card
From the Hugging Face model README
The model is pretrained on the OSCAR dataset for Bangla, English and Hindi. And further pre-trained on 560k code-mixed data (Bangla-English-Hindi). The base model is Distil-BERT and the intended use for this model is for the datasets that contain a Code-mixing of these languages.
To cite:
@article{raihan2023mixed, title={Mixed-Distil-BERT: Code-mixed Language Modeling for Bangla, English, and Hindi}, author={Raihan, Md Nishat and Goswami, Dhiman and Mahmud, Antara}, journal={arXiv preprint arXiv:2309.10272}, year={2023} }
- Task
- Fill-Mask
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Sep 17, 2023
- Updated
- Sep 26, 2023