Upload tokenizer

special_tokens_map.json

@@ -1,6 +1,10 @@
 {
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
   "bos_token": "<s>",
-  "cls_token": "<s>",
+  "cls_token": "<cls>",
   "eos_token": "</s>",
   "mask_token": {
     "content": "<mask>",
@@ -10,6 +14,6 @@
     "single_word": false
   },
   "pad_token": "<pad>",
-  "sep_token": "</s>",
+  "sep_token": "<sep>",
   "unk_token": "<unk>"
 }

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
+size 798011

tokenizer_config.json

@@ -1,15 +1,26 @@
 {
-  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
+  "cls_token": "<cls>",
+  "do_lower_case": false,
   "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
-  "model_max_length": 512,
+  "keep_accents": false,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
+  "remove_space": true,
+  "sep_token": "<sep>",
+  "tokenizer_class": "XLNetTokenizer",
   "unk_token": "<unk>"
 }