Text Classification
Transformers
Safetensors
Russian
roberta
russian
toxicity
text-embeddings-inference
Instructions to use dimkonn/russian-toxic-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dimkonn/russian-toxic-classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="dimkonn/russian-toxic-classifier")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("dimkonn/russian-toxic-classifier") model = AutoModelForSequenceClassification.from_pretrained("dimkonn/russian-toxic-classifier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
metadata
library_name: transformers
tags:
- russian
- toxicity
- text-classification
- roberta
license: mit
language:
- ru
datasets:
- Mnwa/russian-toxic
base_model:
- ai-forever/ru-en-RoSBERTa
pipeline_tag: text-classification
Russian Toxic Classifier
Модель бинарной классификации токсичности текстов на базе ai-forever/ru-en-RoSBERTa.
Метрики (test)
- Accuracy: 0.9186
- F1: 0.9162
- ROC AUC: 0.9765
Использование
from transformers import pipeline
classifier = pipeline("text-classification", model="dimkonn/russian-toxic-classifier")
result = classifier("Вы что, совсем тупой?")
print(result)