Upload tokenizer

added_tokens.json

@@ -1,7 +1,3 @@
 {
-  "</s>": 2,
-  "<mask>": 64000,
-  "<pad>": 1,
-  "<s>": 0,
-  "<unk>": 3
+  "<mask>": 64000
 }

special_tokens_map.json

@@ -1,16 +1,51 @@
 {
-  "additional_special_tokens": [
-    "<s>",
-    "<pad>",
-    "</s>",
-    "<unk>",
-    "<mask>"
-  ],
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -41,13 +41,6 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<s>",
-    "<pad>",
-    "</s>",
-    "<unk>",
-    "<mask>"
-  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
@@ -57,6 +50,5 @@
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "tokenizer_class": "PhobertTokenizer",
-  "tokenizer_file": null,
   "unk_token": "<unk>"
 }