Upload tokenizer

README.md

@@ -1,15 +1,15 @@
 ---
-license: apache-2.0
 datasets:
-  - lmms-lab/LLaVA-OneVision-Data
+- lmms-lab/LLaVA-OneVision-Data
 language:
-  - en
-  - zh
-metrics:
-  - accuracy
+- en
+- zh
 library_name: transformers
+license: apache-2.0
+metrics:
+- accuracy
 tags:
-  - multimodal
+- multimodal
 ---
 
 # LLaVA-OneVision

added_tokens.json

@@ -1,4 +1,5 @@
 {
+  "<image>": 151646,
   "<|endoftext|>": 151643,
   "<|im_end|>": 151645,
   "<|im_start|>": 151644

tokenizer.json

@@ -29,6 +29,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 151646,
+      "content": "<image>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {
@@ -73,6 +82,7 @@
     "end_of_word_suffix": "",
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "!": 0,
       "\"": 1,

tokenizer_config.json

@@ -24,6 +24,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "151646": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [