Commit
·
7b384a1
1
Parent(s):
31ce9d6
Adding phishing detection model and tokenizer
Browse files- .gitattributes +1 -0
- config.json +2 -14
- model.safetensors +2 -2
- temp_dir/ALL-phishing-links.txt +3 -0
- temp_dir/phishing-links.tar.gz +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
temp_dir/ALL-phishing-links.txt filter=lfs diff=lfs merge=lfs -text
|
config.json
CHANGED
|
@@ -2,36 +2,26 @@
|
|
| 2 |
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
"activation": "gelu",
|
| 4 |
"architectures": [
|
| 5 |
-
"
|
| 6 |
],
|
| 7 |
"attention_dropout": 0.1,
|
| 8 |
-
"attention_probs_dropout_prob": 0.1,
|
| 9 |
-
"classifier_dropout": null,
|
| 10 |
"dim": 768,
|
| 11 |
"dropout": 0.1,
|
| 12 |
-
"hidden_act": "gelu",
|
| 13 |
"hidden_dim": 3072,
|
| 14 |
-
"hidden_dropout_prob": 0.1,
|
| 15 |
-
"hidden_size": 768,
|
| 16 |
"id2label": {
|
| 17 |
"0": "benign",
|
| 18 |
"1": "phishing"
|
| 19 |
},
|
| 20 |
"initializer_range": 0.02,
|
| 21 |
-
"intermediate_size": 3072,
|
| 22 |
"label2id": {
|
| 23 |
"benign": 0,
|
| 24 |
"phishing": 1
|
| 25 |
},
|
| 26 |
-
"layer_norm_eps": 1e-12,
|
| 27 |
"max_position_embeddings": 512,
|
| 28 |
-
"model_type": "
|
| 29 |
"n_heads": 12,
|
| 30 |
"n_layers": 6,
|
| 31 |
-
"num_attention_heads": 12,
|
| 32 |
-
"num_hidden_layers": 12,
|
| 33 |
"pad_token_id": 0,
|
| 34 |
-
"position_embedding_type": "absolute",
|
| 35 |
"problem_type": "single_label_classification",
|
| 36 |
"qa_dropout": 0.1,
|
| 37 |
"seq_classif_dropout": 0.2,
|
|
@@ -39,7 +29,5 @@
|
|
| 39 |
"tie_weights_": true,
|
| 40 |
"torch_dtype": "float32",
|
| 41 |
"transformers_version": "4.37.2",
|
| 42 |
-
"type_vocab_size": 2,
|
| 43 |
-
"use_cache": true,
|
| 44 |
"vocab_size": 30522
|
| 45 |
}
|
|
|
|
| 2 |
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
"activation": "gelu",
|
| 4 |
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
],
|
| 7 |
"attention_dropout": 0.1,
|
|
|
|
|
|
|
| 8 |
"dim": 768,
|
| 9 |
"dropout": 0.1,
|
|
|
|
| 10 |
"hidden_dim": 3072,
|
|
|
|
|
|
|
| 11 |
"id2label": {
|
| 12 |
"0": "benign",
|
| 13 |
"1": "phishing"
|
| 14 |
},
|
| 15 |
"initializer_range": 0.02,
|
|
|
|
| 16 |
"label2id": {
|
| 17 |
"benign": 0,
|
| 18 |
"phishing": 1
|
| 19 |
},
|
|
|
|
| 20 |
"max_position_embeddings": 512,
|
| 21 |
+
"model_type": "distilbert",
|
| 22 |
"n_heads": 12,
|
| 23 |
"n_layers": 6,
|
|
|
|
|
|
|
| 24 |
"pad_token_id": 0,
|
|
|
|
| 25 |
"problem_type": "single_label_classification",
|
| 26 |
"qa_dropout": 0.1,
|
| 27 |
"seq_classif_dropout": 0.2,
|
|
|
|
| 29 |
"tie_weights_": true,
|
| 30 |
"torch_dtype": "float32",
|
| 31 |
"transformers_version": "4.37.2",
|
|
|
|
|
|
|
| 32 |
"vocab_size": 30522
|
| 33 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5497eb74ec73c9b5a2569a3144d0a2613d81b0c25512021dae20d1aff61ec35d
|
| 3 |
+
size 267832560
|
temp_dir/ALL-phishing-links.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:444c65912ed1188bc471d42142440ec8901a92d2c4099d7b2d35e3b162f78d12
|
| 3 |
+
size 86542068
|
temp_dir/phishing-links.tar.gz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c12d4723839de2da3f461503520b4c40a4f23a7ccdd33851ae9e01ecc23ad00
|
| 3 |
+
size 25483948
|