update tokenizer config

special_tokens_map.json

@@ -23,12 +23,5 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
   }
 }

tokenizer.json

@@ -129,7 +129,7 @@
   "model": {
     "type": "BPE",
     "dropout": null,
-    "unk_token": "<unk>",
+    "unk_token": null,
     "continuing_subword_prefix": null,
     "end_of_word_suffix": null,
     "fuse_unk": true,

tokenizer_config.json

@@ -46,6 +46,6 @@
   "tokenizer_class": "LlamaTokenizer",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
-  "unk_token": "<unk>",
+  "unk_token": null,
   "use_default_system_prompt": false
 }