Upload processor

image_preprocessing_molmo.py

@@ -563,4 +563,7 @@ class MolmoImageProcessor(BaseImageProcessor):
         }
         if image_masks is not None:
             out["image_masks"] = image_masks
-        return out
+        return out
+
+
+MolmoImageProcessor.register_for_auto_class()

preprocessing_molmo.py

@@ -4,6 +4,7 @@ Processor class for Molmo.
 
 from typing import List, Union, Optional
 
+from transformers.utils.constants import OPENAI_CLIP_STD, OPENAI_CLIP_MEAN
 
 try:
     from typing import Unpack
@@ -24,7 +25,7 @@ from transformers.tokenization_utils_base import TextInput
 from transformers.utils import logging
 
 from transformers import AutoTokenizer
-from hf_molmo.image_preprocessing_molmo import MolmoImagesKwargs, make_batched_images, MolmoImageProcessor
+from .image_preprocessing_molmo import MolmoImagesKwargs, make_batched_images, MolmoImageProcessor
 
 
 logger = logging.get_logger(__name__)
@@ -79,12 +80,13 @@ class MolmoProcessorKwargs(ProcessingKwargs, total=False):
 
 class MolmoProcessor(ProcessorMixin):
     attributes = ["image_processor", "tokenizer"]
-    image_processor_class = "MolmoImageProcessor"
+    image_processor_class = "AutoImageProcessor"
     tokenizer_class = ("Qwen2Tokenizer", "Qwen2TokenizerFast")
 
     def __init__(self, image_processor: MolmoImageProcessor = None, tokenizer : AutoTokenizer = None, **kwargs):
-        self.image_processor = image_processor
-        self.tokenizer = tokenizer
+        # self.image_processor = image_processor
+        # self.tokenizer = tokenizer
+        super().__init__(image_processor, tokenizer)
         self._special_tokens = None
 
     @property
@@ -169,4 +171,5 @@ class MolmoProcessor(ProcessorMixin):
 
         return out
 
-    MolmoProcessor.register_for_auto_class()
+
+MolmoProcessor.register_for_auto_class()

preprocessor_config.json

@@ -1,4 +1,8 @@
 {
+  "auto_map": {
+    "AutoImageProcessor": "image_preprocessing_molmo.MolmoImageProcessor",
+    "AutoProcessor": "preprocessing_molmo.MolmoProcessor"
+  },
   "base_image_input_size": [
     336,
     336

processor_config.json

@@ -0,0 +1,6 @@
+{
+  "auto_map": {
+    "AutoProcessor": "preprocessing_molmo.MolmoProcessor"
+  },
+  "processor_class": "MolmoProcessor"
+}

tokenizer_config.json

@@ -73,6 +73,9 @@
     "<im_col>",
     "<|image|>"
   ],
+  "auto_map": {
+    "AutoProcessor": "preprocessing_molmo.MolmoProcessor"
+  },
   "bos_token": null,
   "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,