Fix tokenizer.

special_tokens_map.json

@@ -1,4 +1,23 @@
 {
-  "bos_token": "<|begin_of_text|>",
-  "eos_token": "<|end_of_text|>"
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -2300,7 +2300,7 @@
     },
     {
       "id": 128255,
-      "content": "<|reserved_special_token_250|>",
+      "content": "<pad>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -2348,6 +2348,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "!": 0,
       "\"": 1,
@@ -410500,4 +410501,4 @@
       "éĶ ¦"
     ]
   }
-}
+}

tokenizer_config.json

@@ -2060,4 +2060,4 @@
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "tokenizer_class": "PreTrainedTokenizerFast"
-}
+}