Upload v2 of URL classifier model

Metrics:
- Test Accuracy: 0.9959
- Test F1: 0.9959
- Test FPR: 0.0061
- Test FNR: 0.0024

special_tokens_map.json

@@ -1,4 +1,10 @@
 {
+  "additional_special_tokens": [
+    "[DOMAIN]",
+    "[PATH]",
+    "[IP]",
+    "[IPv6]"
+  ],
   "cls_token": {
     "content": "[CLS]",
     "lstrip": false,

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "[UNK]",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -39,27 +39,59 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "5": {
+      "content": "[DOMAIN]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[PATH]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "[IP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "[IPv6]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
+  "additional_special_tokens": [
+    "[DOMAIN]",
+    "[PATH]",
+    "[IP]",
+    "[IPv6]"
+  ],
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
-  "max_len": 64,
   "max_length": 64,
-  "model_max_length": 64,
-  "never_split": null,
+  "model_max_length": 1024,
   "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
   "pad_token_type_id": 0,
   "padding_side": "right",
   "sep_token": "[SEP]",
   "stride": 0,
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "PreTrainedTokenizerFast",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"