README.md

---
license: mit
language:
- en
base_model:
- CrabInHoney/urlbert-tiny-base-v1
pipeline_tag: text-classification
tags:
- classification
- url
- urls
- phishing
new_version: CrabInHoney/urlbert-tiny-v2-phishing-classifier
---
This is a very small version of BERT, designed to categorize links into phishing and non-phishing links

Model size
6.53M params

Tensor type
F32

[Dataset](https://www.kaggle.com/datasets/taruntiwarihp/phishing-site-urls "Dataset")

Example:

    from transformers import BertTokenizerFast, BertForSequenceClassification, pipeline
    import torch
    
    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    print(f"Используемое устройство: {device}")
    
    model_path = "./urlbert-tiny-v1-phishing-classifier"
    
    tokenizer = BertTokenizerFast.from_pretrained(model_path)
    
    model = BertForSequenceClassification.from_pretrained(model_path)
    model.to(device)
    
    classifier = pipeline(
        "text-classification",
        model=model,
        tokenizer=tokenizer,
        device=0 if torch.cuda.is_available() else -1,
        return_all_scores=True
    )
    
    test_urls = [
        "en.wikipedia.org/wiki/",
        "facebook-profile.km6.net"
    ]
    
    for url in test_urls:
        results = classifier(url)
        print(f"\nURL: {url}")
        for result in results[0]:
            label = result['label']
            score = result['score']
            print(f"Класс: {label}, вероятность: {score:.4f}")
			

Output:

Используемое устройство: cuda

URL: en.wikipedia.org/wiki/

Класс: good, вероятность: 0.9995

Класс: phish, вероятность: 0.0005


URL: facebook-profile.km6.net

Класс: good, вероятность: 0.0012

Класс: phish, вероятность: 0.9988

## License

[MIT](https://choosealicense.com/licenses/mit/)