Upload tokenizer

special_tokens_map.json

@@ -15,7 +15,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "sep_token": "</s>",
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -12,6 +17,15 @@
       "normalized": false,
       "special": true
     },
+    {
+      "id": 1,
+      "content": "<s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
     {
       "id": 2,
       "content": "</s>",
@@ -21,6 +35,15 @@
       "normalized": false,
       "special": true
     },
+    {
+      "id": 3,
+      "content": "<mask>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
     {
       "id": 15999,
       "content": "<pad>",
@@ -59,15 +82,58 @@
     "split": true
   },
   "post_processor": {
-    "type": "BertProcessing",
-    "sep": [
-      "<s>",
-      1
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 0
+        }
+      }
     ],
-    "cls": [
-      "</s>",
-      2
-    ]
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 0
+        }
+      }
+    ],
+    "special_tokens": {
+      "</s>": {
+        "id": "</s>",
+        "ids": [
+          2
+        ],
+        "tokens": [
+          "</s>"
+        ]
+      }
+    }
   },
   "decoder": {
     "type": "Metaspace",

tokenizer_config.json

@@ -9,6 +9,14 @@
       "single_word": false,
       "special": true
     },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
     "2": {
       "content": "</s>",
       "lstrip": false,
@@ -17,6 +25,14 @@
       "single_word": false,
       "special": true
     },
+    "3": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
     "15999": {
       "content": "<pad>",
       "lstrip": false,