Upload tokenizer

added_tokens.json

@@ -1,3 +1,7 @@
 {
-  "<|endoftext|>": 6881
+  "</s>": 6882,
+  "<mask>": 6885,
+  "<pad>": 6884,
+  "<s>": 6881,
+  "<unk>": 6883
 }

special_tokens_map.json

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

tokenizer.json

@@ -50,12 +50,48 @@
     },
     {
       "id": 6881,
-      "content": "<|endoftext|>",
+      "content": "<s>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 6882,
+      "content": "</s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 6883,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 6884,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 6885,
+      "content": "<mask>",
+      "single_word": false,
+      "lstrip": true,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -1,11 +1,15 @@
 {
   "add_prefix_space": false,
-  "bos_token": "<|endoftext|>",
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "max_length": 100,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
-  "padding_side": "right",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
 }