Upload tokenizer

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "</s>": 25001,
+  "<mask>": 25004,
+  "<pad>": 25003,
+  "<s>": 25000,
+  "<unk>": 25002
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "labels": false,
+  "mask_token": "<mask>",
+  "max_len": 128,
+  "model_max_length": 128,
+  "name_or_path": "/content/tokenizer_loc",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>",
+  "use_fast": true
+}