token_alignment (#13)

- tokenizer alignment (48d1631122017c80068ff7cf45d1138820a6142b)

special_tokens_map.json

@@ -13,13 +13,6 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false
-    },
-    {
-      "content": "<end_of_utterance>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
     }
   ],
   "bos_token": {

tokenizer.json

@@ -866,15 +866,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 100352,
-      "content": "<end_of_utterance>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -769,20 +769,11 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "100352": {
-      "content": "<end_of_utterance>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "additional_special_tokens": [
     "<fake_token_around_image>",
-    "<image>",
-    "<end_of_utterance>"
+    "<image>"
   ],
   "bos_token": "<|start_of_role|>",
   "clean_up_tokenization_spaces": false,