Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 912,
+  "<s>": 911
+}

special_tokens_map.json

@@ -1,5 +1,7 @@
 {
+  "bos_token": "<s>",
   "cls_token": "[CLS]",
+  "eos_token": "</s>",
   "mask_token": "[MASK]",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",

tokenizer_config.json

@@ -39,12 +39,30 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "911": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "912": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": false,
+  "eos_token": "</s>",
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
   "never_split": null,
@@ -52,6 +70,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "MobileBertTokenizer",
+  "tokenizer_class": "FunnelTokenizer",
   "unk_token": "[UNK]"
 }