added the tokenizer

README.md

@@ -1,4 +1,14 @@
 ---
+widget:
+- text: 949-959 SOUTHERN BLVD LLC
+- text: Lumico Life Insurance Company of New York
+- text: BNP PARIBAS ASSET MANAGEMENT USA HOLDINGS, INC.
+- text: QB ASSOCIATES, L.P.
+- text: THE LOTOS CLUB
+- text: LOMBARD & GELIBETER LLP
+- text: Walden Savings Bank
+- text: Adirondack Bank
+- text: The North Country Savings Bank
 model-index:
 - name: Sociovestix/lenu_US-NY
   results:
@@ -20,16 +30,6 @@ model-index:
       name: f1 macro
       args:
         average: macro
-widget:
-- text: "949-959 SOUTHERN BLVD LLC"
-- text: "Lumico Life Insurance Company of New York"
-- text: "BNP PARIBAS ASSET MANAGEMENT USA HOLDINGS, INC."
-- text: "QB ASSOCIATES, L.P."
-- text: "THE LOTOS CLUB"
-- text: "LOMBARD & GELIBETER LLP"
-- text: "Walden Savings Bank"
-- text: "Adirondack Bank"
-- text: "The North Country Savings Bank"
 ---
 
 # LENU - Legal Entity Name Understanding for US New York

tokenizer_config.json

@@ -1,14 +1,53 @@
 {
+  "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,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "name_or_path": "yiyanghkust/finbert-pretrain",
-  "never_split": null,
+  "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",