Upload tokenizer

special_tokens_map.json

@@ -1,6 +1,6 @@
 {
-  "bos_token": "BOS",
-  "eos_token": "EOS",
+  "bos_token": "UTT_BOUNDARY",
+  "eos_token": "UTT_BOUNDARY",
   "pad_token": "PAD",
   "unk_token": "UNK"
 }

tokenizer.json

@@ -21,24 +21,6 @@
       "normalized": false,
       "special": true
     },
-    {
-      "id": 2,
-      "content": "BOS",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 3,
-      "content": "EOS",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
     {
       "id": 44,
       "content": "<|endoftext|>",

tokenizer_config.json

@@ -17,22 +17,6 @@
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "BOS",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "EOS",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
     "44": {
       "content": "<|endoftext|>",
       "lstrip": false,
@@ -42,9 +26,9 @@
       "special": true
     }
   },
-  "bos_token": "BOS",
+  "bos_token": "UTT_BOUNDARY",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "EOS",
+  "eos_token": "UTT_BOUNDARY",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "PAD",
   "tokenizer_class": "GPT2Tokenizer",