Fix tokenizer

added_tokens.json

@@ -1,10 +1,7 @@
 {
-  "<im_col>": 151649,
-  "<im_end>": 151647,
-  "<im_patch>": 151648,
-  "<im_start>": 151646,
-  "<|endoftext|>": 151643,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644,
-  "<|image|>": 151650
+  "<im_col>": 100281,
+  "<im_end>": 100279,
+  "<im_patch>": 100280,
+  "<im_start>": 100278,
+  "<|image|>": 100282
 }

special_tokens_map.json

@@ -1,4 +1,37 @@
 {
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<|padding|>"
+  "additional_special_tokens": [
+    "<im_start>",
+    "<im_end>",
+    "<im_patch>",
+    "<im_col>",
+    "<|image|>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -254,6 +254,51 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 50280,
+      "content": "<im_start>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 50281,
+      "content": "<im_end>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 50282,
+      "content": "<im_patch>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 50283,
+      "content": "<im_col>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 50284,
+      "content": "<|image|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -226,7 +226,47 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    }
+    },
+    "50280": {
+      "content": "<im_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50281": {
+      "content": "<im_end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50282": {
+      "content": "<im_patch>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50283": {
+      "content": "<im_col>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50284": {
+      "content": "<|image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }    
   },
   "bos_token": null,
   "clean_up_tokenization_spaces": true,
@@ -235,4 +275,4 @@
   "pad_token": "<|padding|>",
   "tokenizer_class": "GPTNeoXTokenizer",
   "unk_token": null
-}
+}