add tokenizer

special_tokens_map.json

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

tokenizer.json

@@ -67,8 +67,7 @@
   "pre_tokenizer": {
     "type": "ByteLevel",
     "add_prefix_space": false,
-    "trim_offsets": true,
-    "use_regex": true
+    "trim_offsets": true
   },
   "post_processor": {
     "type": "RobertaProcessing",
@@ -86,8 +85,7 @@
   "decoder": {
     "type": "ByteLevel",
     "add_prefix_space": true,
-    "trim_offsets": true,
-    "use_regex": true
+    "trim_offsets": true
   },
   "model": {
     "type": "BPE",

tokenizer_config.json

@@ -1,16 +1 @@
-{
-  "add_prefix_space": false,
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
-  "model_max_length": 512,
-  "name_or_path": "roberta-base",
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "special_tokens_map_file": null,
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
-  "unk_token": "<unk>"
-}
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 512, "name_or_path": "relbert-roberta-base-semeval2012-v6-average-prompt-d-loob-0", "special_tokens_map_file": null, "tokenizer_class": "RobertaTokenizer"}