use real transformers lib and have changes locally

image_processing_kosmos2_5.py

@@ -16,7 +16,7 @@
 
 import math
 from typing import Dict, Optional, Union
-
+from transformers import AutoImageProcessor
 import numpy as np
 
 from transformers.image_processing_utils import BaseImageProcessor, BatchFeature
@@ -338,4 +338,6 @@ class Kosmos2_5ImageProcessor(BaseImageProcessor):
             tensor_type=return_tensors,
         )
 
-        return encoded_outputs
+        return encoded_outputs
+    
+AutoImageProcessor.register("Kosmos2_5ImageProcessor", Kosmos2_5ImageProcessor)

processing_kosmos2_5.py

@@ -17,12 +17,13 @@ Processor class for Kosmos2_5.
 """
 
 from typing import List, Optional, Union
-
+import transformers
 from transformers.image_processing_utils import BatchFeature
 from transformers.processing_utils import ProcessorMixin
 from transformers.tokenization_utils_base import PaddingStrategy, TextInput, TruncationStrategy
 from transformers.utils import TensorType, is_torch_available
-
+from .image_processing_kosmos2_5 import Kosmos2_5ImageProcessor
+transformers.Kosmos2_5ImageProcessor = Kosmos2_5ImageProcessor 
 
 if is_torch_available():
     import torch
@@ -49,7 +50,8 @@ class Kosmos2_5Processor(ProcessorMixin):
 
     def __init__(self, image_processor, tokenizer):
         tokenizer.return_token_type_ids = False
-        super().__init__(image_processor, tokenizer)
+        self.image_processor = image_processor
+        self.tokenizer = tokenizer
 
     def __call__(
         self,

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}