Downloads · 30 days
15
1% of all-time downloads
mT5-base-HunSum-2
SZTAKI-HLT/mT5-base-HunSum-2
mT5-base-HunSum-2 is a summarization model from SZTAKI-HLT. Use it when you need a shorter version of a longer text. It is set up for transformers. The card lists the license as apache-2.0.
The mT5-base-HunSum-2 is a Hungarian abstractive summarization model, which was trained on the SZTAKI-HLT/HunSum-2-abstractive dataset. The model is based on google/mt5-base.
All-time downloads
1.1K
Public
Repo size
7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin2.3 GB · 99%
At a glance
- Task
- Summarization
- Library
- transformers
- License
- apache-2.0
- Model type
- mt5
- Access
- Public
- Created
- Apr 3, 2024
- Updated
- Jan 23, 2025
- SHA
- e88ececb
Base models
Datasets
Model card
From the Hugging Face model README
Model Card for mT5-base-HunSum-2
The mT5-base-HunSum-2 is a Hungarian abstractive summarization model, which was trained on the SZTAKI-HLT/HunSum-2-abstractive dataset. The model is based on google/mt5-base.
Intended uses & limitations
- Model type: Text Summarization
- Language(s) (NLP): Hungarian
- Resource(s) for more information:
Parameters
- Batch Size: 12
- Learning Rate: 5e-5
- Weight Decay: 0.01
- Warmup Steps: 3000
- Epochs: 10
- no_repeat_ngram_size: 3
- num_beams: 5
- early_stopping: False
- encoder_no_repeat_ngram_size: 4
Results
| Metric | Value |
|---|---|
| ROUGE-1 | 40.06 |
| ROUGE-2 | 12.67 |
| ROUGE-L | 25.93 |
- Task
- Summarization
- Library
- transformers
- Type
- mt5
- License
- apache-2.0
- Languages
- hu
- Created
- Apr 3, 2024
- Updated
- Jan 23, 2025