Downloads · 30 days
35
59% of all-time downloads
Werea-TR-Summarizer
Werea-co/Werea-TR-Summarizer
Werea-TR-Summarizer is a summarization model from Werea-co. Use it when you need a shorter version of a longer text. The card lists the license as mit.
Gerçek TR-News haber-özet çiftleriyle (50k) eğitildi, test bölümünde dürüstçe ölçüldü.
All-time downloads
59
Public
Parameters
300M
2.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 GB · 98%
At a glance
- Task
- Summarization
- License
- mit
- Model type
- mt5
- Access
- Public
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026
- SHA
- cdcdaea5
Base models
Datasets
Model card
From the Hugging Face model README
Werea-TR-Summarizer — Türkçe Haber Özetleme
Gerçek TR-News haber-özet çiftleriyle (50k) eğitildi, test bölümünde dürüstçe ölçüldü.
Benchmark (TR-News test, n=400)
| Metrik | Skor |
|---|---|
| ROUGE-1 | 32.5 |
| ROUGE-2 | 20.3 |
| ROUGE-L | 29.4 |
mT5-small tabanlı, prefix özet: .
Kullanım
from transformers import pipeline
s=pipeline("summarization",model="Werea-co/Werea-TR-Summarizer")
print(s("özet: "+haber, max_new_tokens=100, num_beams=4))
💜 werea.co
- Task
- Summarization
- Type
- mt5
- License
- mit
- Languages
- tr
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026