Downloads · 30 days
10
24% of all-time downloads
tr-toxic-bert-multiclass-v1
celalkartoglu/tr-toxic-bert-multiclass-v1
tr-toxic-bert-multiclass-v1 is a machine learning model from celalkartoglu. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Etiketler: DİĞER, KÜFÜR, HAKARET, IRKÇI, CİNSİYETÇİ Veri: Overfit-GM/turkish-toxic-language (77,800 örnek) Taban model: dbmdz/bert-base-turkish-cased Eğitim: 3 epoch, bs=16/32, lr=3e-5, classweight ile dengeleme
All-time downloads
42
Public
Parameters
111M
443 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors443 MB · 100%
At a glance
- Model type
- bert
- Access
- Public
- Created
- Aug 24, 2025
- Updated
- Aug 24, 2025
- SHA
- f8f46c70
Model card
From the Hugging Face model README
Türkçe Toksisite Sınıflandırma — BERTurk (5 sınıf)
Etiketler: DİĞER, KÜFÜR, HAKARET, IRKÇI, CİNSİYETÇİ
Veri: Overfit-GM/turkish-toxic-language (77,800 örnek)
Taban model: dbmdz/bert-base-turkish-cased
Eğitim: 3 epoch, bs=16/32, lr=3e-5, class_weight ile dengeleme
Değerlendirme (Validation)
- Accuracy: 0.9563
- Macro-F1: 0.9185
- Loss: 0.4408
Kullanım
from transformers import AutoTokenizer, AutoModelForSequenceClassification, TextClassificationPipeline
tok = AutoTokenizer.from_pretrained("celalkartoglu/tr-toxic-bert-multiclass-v1")
mdl = AutoModelForSequenceClassification.from_pretrained("celalkartoglu/tr-toxic-bert-multiclass-v1")
pipe = TextClassificationPipeline(model=mdl, tokenizer=tok, top_k=1)
pipe("Defol git buradan.") # -> [{'label': 'HAKARET', 'score': ...}]
- Type
- bert
- Created
- Aug 24, 2025
- Updated
- Aug 24, 2025