Upload tokenizer

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "[MASK]",
+  "pad_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "sep_token": {
     "content": "[SEP]",
     "lstrip": false,

tokenizer_config.json

@@ -949,13 +949,20 @@
   "cls_token": "[CLS]",
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
+  "max_length": 179,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 179,
+  "pad_to_multiple_of": null,
   "pad_token": "[MASK]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
+  "stride": 0,
   "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }