ruAntiToxic_v1
NeuroSpaceX/ruAntiToxic_v1 — модель для классификации русского текста на токсичный и нетоксичный.
Установка
pip install transformers torch
Использование
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
tokenizer = AutoTokenizer.from_pretrained("NeuroSpaceX/ruAntiToxic_v1")
model = AutoModelForSequenceClassification.from_pretrained("NeuroSpaceX/ruAntiToxic_v1")
text = "Ваш тестовый текст"
inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
logits = model(**inputs).logits.squeeze()
score = torch.sigmoid(logits).item()
label = "токсичный" if score > 0.5 else "нетоксичный"
print(label, score)
- Downloads last month
- 13
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for NeuroSpaceX/ruAntiToxic_v1
Base model
cointegrated/rubert-tiny2