Upload v2 of URL classifier model

Training Metrics:
- Eval Loss: 0.033418405801057816
- Eval F1: 0.9921365145524408

special_tokens_map.json

@@ -1,10 +1,4 @@
 {
-  "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": "[UNK]",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "[PAD]",
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -39,59 +39,27 @@
       "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": 1024,
+  "model_max_length": 64,
+  "never_split": null,
   "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
   "pad_token_type_id": 0,
   "padding_side": "right",
   "sep_token": "[SEP]",
   "stride": 0,
-  "tokenizer_class": "PreTrainedTokenizerFast",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"