Upload processor

special_tokens_map.json

@@ -424,7 +424,7 @@
     "<im_col>",
     "<|image|>"
   ],
-  "boi_token": "<im_patch>",
+  "boi_token": "<im_start>",
   "bos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
@@ -432,7 +432,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "eoi_token": "<im_start>",
+  "eoi_token": "<im_end>",
   "eos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
@@ -441,7 +441,7 @@
     "single_word": false
   },
   "im_col_token": "<im_col>",
-  "im_patch_token": "<im_end>",
+  "im_patch_token": "<im_patch>",
   "image_token": "<image>",
   "pad_token": {
     "content": "<|endoftext|>",

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c185be0abfb0c75ad6c5f73b216b8652e1b6d0f5288477b1f96b7f3e2754907
-size 11501784
+oid sha256:ec9836c15b34f4d6e1c2324574589d9886de43d5ba3339b27c5be18ed8a9c0df
+size 11501616

tokenizer_config.json

@@ -3846,22 +3846,22 @@
   "auto_map": {
     "AutoProcessor": "preprocessing_molmo.MolmoProcessor"
   },
-  "boi_token": "<im_patch>",
+  "boi_token": "<im_start>",
   "bos_token": "<|endoftext|>",
   "chat_template": "{% for message in messages -%}\n        {%- if (loop.index % 2 == 1 and message['role'] != 'user') or \n          (loop.index % 2 == 0 and message['role'].lower() != 'assistant') -%}\n        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}\n        {%- endif -%}\n        {{ message['role'].capitalize() + ': ' + message['content'] }}\n        {%- if not loop.last -%}\n        {{ ' ' }}\n        {%- endif %}\n        {%- endfor -%}\n        {%- if add_generation_prompt -%}\n        {{ ' Assistant:' }}\n        {%- endif %}",
   "clean_up_tokenization_spaces": false,
-  "eoi_token": "<im_start>",
+  "eoi_token": "<im_end>",
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "extra_special_tokens": {
-    "boi_token": "<im_patch>",
-    "eoi_token": "<im_start>",
+    "boi_token": "<im_start>",
+    "eoi_token": "<im_end>",
     "im_col_token": "<im_col>",
-    "im_patch_token": "<im_end>",
+    "im_patch_token": "<im_patch>",
     "image_token": "<image>"
   },
   "im_col_token": "<im_col>",
-  "im_patch_token": "<im_end>",
+  "im_patch_token": "<im_patch>",
   "image_token": "<image>",
   "model_max_length": 32768,
   "pad_token": "<|endoftext|>",