RUSpam/spam_deberta_v4

Описание

Это модель определения спама, основанная на архитектуре Deberta, дообученная на русскоязычных данных о спаме. Она классифицирует текст как спам или не спам.

Использование

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model_path = "RUSpam/spam_deberta_v4"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForSequenceClassification.from_pretrained(model_path)

def predict(text):
    inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=256)
    with torch.no_grad():
        outputs = model(**inputs)
        logits = outputs.logits
        predicted_class = torch.argmax(logits, dim=1).item()
    return "Спам" if predicted_class == 1 else "Не спам"

text = "Ваш текст для проверки здесь"
result = predict(text)
print(f"Результат: {result}")

Цитирование

@MISC{RUSpam/spam_deberta_v4,
    author  = {Denis Petrov, Kirill Fedko (Neurospacex),  Sergey Yalovegin},
    title   = {Russian Spam Classification Model},
    url     = {https://huggingface.co/RUSpam/spam_deberta_v4/},
    year    = 2024
}
Downloads last month
745
Safetensors
Model size
82.1M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Space using RUSpam/spam_deberta_v4 1

Evaluation results