Upload README.md

README.md

@@ -1,3 +1,76 @@
----
-license: mit
----
+This is a very small version of BERT, designed to categorize links into phishing and non-phishing links
+
+Val score: 0.9622
+
+Model size
+
+3.7M params
+
+Tensor type
+
+F32
+
+[Dataset](https://huggingface.co/datasets/ealvaradob/phishing-dataset "Dataset")
+(urls.json only)
+
+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-v2-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 = [
+        "huggingface.co/",
+        "p64.hu991ngface.co.com.ru/"
+    ]
+    
+    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: huggingface.co/
+
+Класс: good, вероятность: 0.8515
+
+Класс: phish, вероятность: 0.1485
+
+
+
+URL: p64.hu991ngface.co.com.ru/
+
+Класс: good, вероятность: 0.0289
+
+Класс: phish, вероятность: 0.9711
+
+
+
+
+## License
+
+[MIT](https://choosealicense.com/licenses/mit/)