update extra special tokens

preprocessor_config.json

@@ -10,7 +10,7 @@
     0.5,
     0.5
   ],
-  "image_processor_type": "Idefics3ImageProcessor",
+  "image_processor_type": "SmolVLMImageProcessor",
   "image_std": [
     0.5,
     0.5,
@@ -19,15 +19,17 @@
   "max_image_size": {
     "longest_edge": 512
   },
-  "video_sampling": {
-    "fps": 1,
-    "max_frames": 64,
-    "video_size": {"longest_edge": 384}
-  },
   "processor_class": "SmolVLMProcessor",
   "resample": 1,
   "rescale_factor": 0.00392156862745098,
   "size": {
     "longest_edge": 2048
+  },
+  "video_sampling": {
+    "fps": 1,
+    "max_frames": 64,
+    "video_size": {
+      "longest_edge": 384
+    }
   }
 }

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": "<|im_start|>",
@@ -29,6 +11,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "end_of_utterance_token": "<end_of_utterance>",
   "eos_token": {
     "content": "<end_of_utterance>",
     "lstrip": false,
@@ -36,6 +19,9 @@
     "rstrip": false,
     "single_word": false
   },
+  "fake_image_token": "<fake_token_around_image>",
+  "global_image_token": "<global-img>",
+  "image_token": "<image>",
   "pad_token": {
     "content": "<|im_end|>",
     "lstrip": false,

tokenizer_config.json

@@ -1170,12 +1170,21 @@
   "bos_token": "<|im_start|>",
   "chat_template": "<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
+  "end_of_utterance_token": "<end_of_utterance>",
   "eos_token": "<end_of_utterance>",
-  "extra_special_tokens": {},
+  "extra_special_tokens": {
+    "end_of_utterance_token": "<end_of_utterance>",
+    "fake_image_token": "<fake_token_around_image>",
+    "global_image_token": "<global-img>",
+    "image_token": "<image>"
+  },
+  "fake_image_token": "<fake_token_around_image>",
+  "global_image_token": "<global-img>",
+  "image_token": "<image>",
   "legacy": false,
   "model_max_length": 8192,
   "pad_token": "<|im_end|>",
-  "processor_class": "Idefics3Processor",
+  "processor_class": "SmolVLMProcessor",
   "tokenizer_class": "GPT2Tokenizer",
   "truncation_side": "left",
   "unk_token": "<|endoftext|>",