Upload tokenizer

special_tokens_map.json

@@ -1,12 +1,5 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
     {
       "content": "<RULING>",
       "lstrip": false,
@@ -14,13 +7,6 @@
       "rstrip": false,
       "single_word": false
     },
-    {
-      "content": "<mask>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
     {
       "content": "<BLANK_SPACE>",
       "lstrip": false,
@@ -42,13 +28,6 @@
       "rstrip": false,
       "single_word": false
     },
-    {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
     {
       "content": "<COLUMN>",
       "lstrip": false,
@@ -69,13 +48,6 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false
-    },
-    {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
     }
   ],
   "bos_token": {

tokenizer.json

@@ -765,25 +765,8 @@
       "𒔲": 628,
       "𒔸": 629,
       "𒕁": 630,
-      "𒕂": 631,
-      "𒌨𒀭": 632,
-      "𒀭𒂗": 633,
-      "𒐊𒋡": 634,
-      "𒋗𒃸": 635,
-      "𒆠𒁀": 636,
-      "𒀭𒂗𒍪": 637,
-      "𒀭𒎏": 638,
-      "𒅆𒌨": 639
+      "𒕂": 631
     },
-    "merges": [
-      "𒌨 𒀭",
-      "𒀭 𒂗",
-      "𒐊 𒋡",
-      "𒋗 𒃸",
-      "𒆠 𒁀",
-      "𒀭𒂗 𒍪",
-      "𒀭 𒎏",
-      "𒅆 𒌨"
-    ]
+    "merges": []
   }
 }

tokenizer_config.json

@@ -90,17 +90,13 @@
     }
   },
   "additional_special_tokens": [
-    "</s>",
     "<RULING>",
-    "<mask>",
     "<BLANK_SPACE>",
     "<unk>",
     "\n",
-    "<s>",
     "<COLUMN>",
     "<SURFACE>",
-    "...",
-    "<pad>"
+    "..."
   ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,