Upload tokenizer

special_tokens_map.json

@@ -1,6 +1,17 @@
 {
-  "bos_token": "<|endoftext|>",
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
   "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "pad_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -1,33 +1,7 @@
 {
-  "add_bos_token": false,
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
   "clean_up_tokenization_spaces": true,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "errors": "replace",
+  "eos_token": "<|endoftext|>",
   "model_max_length": 2048,
-  "pad_token": null,
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }