Upload tokenizer

special_tokens_map.json

@@ -1 +1,7 @@
-{}
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>"
+}

tokenizer.json

@@ -128,6 +128,7 @@
     "continuing_subword_prefix": null,
     "end_of_word_suffix": "</w>",
     "fuse_unk": false,
+    "byte_fallback": false,
     "vocab": {
       "<s>": 0,
       "<pad>": 1,

tokenizer_config.json

@@ -1,4 +1,10 @@
 {
-  "model_max_length": 1000000000000000019884624838656,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "special_tokens_map_file": "data/converted_model_mlm_huggingface/special_tokens_map.json",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }