Upload tokenizer

special_tokens_map.json

@@ -1,4 +1,4 @@
 {
   "eos_token": "<|endoftext|>",
-  "pad_token": "<pad>"
+  "pad_token": "<|endoftext|>"
 }

tokenizer.json

@@ -11,15 +11,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 26,
-      "content": "<pad>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": null,
@@ -55,10 +46,8 @@
       "B": 21,
       "BB": 22,
       "BBB": 23,
-      "<|endoftext|>": 24,
-      "<unk>": 25,
-      "<pad>": 26
+      "<|endoftext|>": 24
     },
-    "unk_token": "<unk>"
+    "unk_token": "<|endoftext|>"
   }
 }

tokenizer_config.json

@@ -7,20 +7,12 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "26": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "PreTrainedTokenizer"
 }