Downloads · 30 days
11
4% of all-time downloads
ModernBERT-base-hungarian
GaborMadarasz/ModernBERT-base-hungarian
ModernBERT-base-hungarian is a fill-mask model from GaborMadarasz. Use it when you need the model to fill a missing word. The card lists the license as apache-2.0.
Model & tokenizer pretrained from scratch (MLM task) only on cleaned(removal of toxic and sexual content, automatic language correctness filtering) and semantically segmented Hungarian text.
All-time downloads
300
Public
Parameters
151M
604 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors604 MB · 99%
At a glance
- Task
- Fill-Mask
- License
- apache-2.0
- Model type
- modernbert
- Access
- Public
- Created
- May 23, 2025
- Updated
- Jul 20, 2025
- SHA
- 4b60089b
Base models
Datasets
Model card
From the Hugging Face model README
Hungarian ModernBERT-base
Model & tokenizer pretrained from scratch (MLM task) only on cleaned(removal of toxic and sexual content, automatic language correctness filtering) and semantically segmented Hungarian text.
Vocab: 52k
Context length of up to 8,192 tokens
Train dataset: ~1billion tokens
- Task
- Fill-Mask
- Type
- modernbert
- License
- apache-2.0
- Languages
- hu
- Created
- May 23, 2025
- Updated
- Jul 20, 2025