Upload processor

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<end_of_utterance>": 32002,
+  "<fake_token_around_image>": 32000,
+  "<image>": 32001
+}

special_tokens_map.json

@@ -1,26 +1,8 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "<fake_token_around_image>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<image>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<end_of_utterance>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+    "<fake_token_around_image>",
+    "<image>",
+    "<end_of_utterance>"
   ],
   "bos_token": {
     "content": "<s>",

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -59,9 +59,8 @@
   "bos_token": "<s>",
   "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. {% for message in messages %}{% if message['role'] == 'user' %}USER: {% else %}ASSISTANT: {% endif %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<image>{% endif %}{% endfor %}{% if message['role'] == 'user' %} {% else %}{{eos_token}}{% endif %}{% endfor %}{% if add_generation_prompt %}ASSISTANT: {% endif %}",
   "clean_up_tokenization_spaces": false,
-  "do_image_splitting": true,
   "eos_token": "</s>",
-  "legacy": true,
+  "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<unk>",
   "processor_class": "Idefics2Processor",