Upload folder using huggingface_hub

README.md

@@ -0,0 +1,71 @@
+---
+language: en
+license: mit
+tags:
+- url-phishing-detection
+- tinybert
+- sequence-classification
+datasets:
+- custom
+metrics:
+- accuracy
+- f1
+---
+
+# TinyBERT for URL Phishing Detection
+
+This model is fine-tuned from huawei-noah/TinyBERT_General_4L_312D to detect phishing URLs.
+
+## Model description
+
+The model is a fine-tuned version of TinyBERT, specifically trained to classify URLs as either legitimate or phishing.
+
+## Intended uses & limitations
+
+This model is intended to be used for detecting phishing URLs. It takes a URL as input and outputs a prediction of whether the URL is legitimate or phishing.
+
+## Training data
+
+The model was trained on a combination of:
+- Legitimate URLs from the Majestic Million dataset
+- Phishing URLs from phishing-links-ACTIVE.txt and phishing-links-INACTIVE.txt
+
+## Training procedure
+
+The model was fine-tuned using the Hugging Face Transformers library with the following parameters:
+- Learning rate: 5e-5
+- Batch size: 16
+- Number of epochs: 3
+- Weight decay: 0.01
+
+## Evaluation results
+
+The model was evaluated on a test set consisting of both legitimate and phishing URLs.
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("songhieng/TinyBERT-URL-Detection-1.0")
+model = AutoModelForSequenceClassification.from_pretrained("songhieng/TinyBERT-URL-Detection-1.0")
+
+# Prepare URL for classification
+url = "https://example.com"
+inputs = tokenizer(url, return_tensors="pt", truncation=True, padding=True, max_length=128)
+
+# Make prediction
+with torch.no_grad():
+    outputs = model(**inputs)
+    predictions = torch.softmax(outputs.logits, dim=1)
+    label = torch.argmax(predictions, dim=1).item()
+
+# Output result
+result = "phishing" if label == 1 else "legitimate"
+confidence = predictions[0][label].item()
+print(f"URL: {url}")
+print(f"Prediction: {result}")
+print(f"Confidence: {confidence:.4f}")
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "cell": {},
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "initializer_range": 0.02,
+  "intermediate_size": 1200,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "pre_trained": "",
+  "problem_type": "single_label_classification",
+  "structure": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d3ecc287eed1118eb9c7adeab30f62925dcfb3986317ad0367e638ff7897624
+size 57411808

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}