Fixed tokenizer_config.json

Fixed tokenizer_config.json's inconsistent BOS, UNK token contents.

tokenizer_config.json

@@ -3,7 +3,7 @@
   "add_prefix_space": false,
   "bos_token": {
     "__type": "AddedToken",
-    "content": "<|endoftext|>",
+    "content": "<||bos||>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
@@ -25,7 +25,7 @@
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": {
     "__type": "AddedToken",
-    "content": "<|endoftext|>",
+    "content": "<||unk||>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,