Downloads · 30 days
49
2% of all-time downloads
SRoBERTa
Andrija/SRoBERTa
SRoBERTa is a fill-mask model from Andrija. 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.
Trained on 0.7GB dataset Croatian and Serbian language for one epoch. Dataset from Leipzig Corpora.
All-time downloads
2.1K
Public
Repo size
963 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin482 MB · 99%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- roberta
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Jan 1, 2023
- SHA
- 41d64afb
Try a prompt
Datasets
Model card
From the Hugging Face model README
Transformer language model for Croatian and Serbian
Trained on 0.7GB dataset Croatian and Serbian language for one epoch. Dataset from Leipzig Corpora.
Information of dataset
| Model | #params | Arch. | Training data |
|---|---|---|---|
Andrija/SRoBERTa | 120M | First | Leipzig Corpus (0.7 GB of text) |
How to use in code
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("Andrija/SRoBERTa")
model = AutoModelForMaskedLM.from_pretrained("Andrija/SRoBERTa")
- Task
- Fill-Mask
- Library
- transformers
- Type
- roberta
- License
- apache-2.0
- Languages
- hr, sr, multilingual
- Created
- Mar 2, 2022
- Updated
- Jan 1, 2023