@ydshieh
it was working fine till yesterday & today i have got this error:
AttributeError: can't set attribute 'can_save_slow_tokenizer'

library installation:
!pip install transformers
!pip install sentencepiece

system specs:
OS: AWS Sagemaker(Amazon Linux 2, Jupyter Lab 3
(notebook-al2-v2))
Python: 3.10
Transformers: 4.31.0
sentencepiece: 0.1.99
PyTorch: 2.0.1
CUDA (python -c 'import torch; print(torch.version.cuda)'): 11.8

code:
import requests

from PIL import Image
from transformers import AutoProcessor, AutoModelForVision2Seq

model = AutoModelForVision2Seq.from_pretrained("ydshieh/kosmos-2-patch14-224", trust_remote_code=True)
processor = AutoProcessor.from_pretrained("ydshieh/kosmos-2-patch14-224", trust_remote_code=True)

prompt = "An image of"

url = "https://huggingface.co/ydshieh/kosmos-2-patch14-224/resolve/main/snowman.png"
image = Image.open(requests.get(url, stream=True).raw)

The original Kosmos-2 demo saves the image first then reload it. For some images, this will give slightly different image input and change the generation outputs.

Uncomment the following 2 lines if you want to match the original demo's outputs.

(One example is the two_dogs.jpg from the demo)

image.save("new_image.jpg")

image = Image.open("new_image.jpg")

inputs = processor(text=prompt, images=image, return_tensors="pt")

generated_ids = model.generate(
pixel_values=inputs["pixel_values"],
input_ids=inputs["input_ids"][:, :-1],
attention_mask=inputs["attention_mask"][:, :-1],
img_features=None,
img_attn_mask=inputs["img_attn_mask"][:, :-1],
use_cache=True,
max_new_tokens=64,
)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]

Specify cleanup_and_extract=False in order to see the raw model generation.

processed_text = processor.post_process_generation(generated_text, cleanup_and_extract=False)

print(processed_text)

<grounding> An image of<phrase> a snowman</phrase><object><patch_index_0044><patch_index_0863></object> warming himself by<phrase> a fire</phrase><object><patch_index_0005><patch_index_0911></object>.

By default, the generated text is cleanup and the entities are extracted.

processed_text, entities = processor.post_process_generation(generated_text)

print(processed_text)

An image of a snowman warming himself by a fire.

print(entities)

[('a snowman', (12, 21), [(0.390625, 0.046875, 0.984375, 0.828125)]), ('a fire', (41, 47), [(0.171875, 0.015625, 0.484375, 0.890625)])]

Error:

AttributeError Traceback (most recent call last)
Cell In[14], line 8
4 from transformers import AutoProcessor, AutoModelForVision2Seq
7 model = AutoModelForVision2Seq.from_pretrained("ydshieh/kosmos-2-patch14-224", trust_remote_code=True)
----> 8 processor = AutoProcessor.from_pretrained("ydshieh/kosmos-2-patch14-224", trust_remote_code=True)
10 prompt = "An image of"
12 url = "https://huggingface.co/ydshieh/kosmos-2-patch14-224/resolve/main/snowman.png"

File ~/anaconda3/envs/pytorch_p310/lib/python3.10/site-packages/transformers/models/auto/processing_auto.py:283, in AutoProcessor.from_pretrained(cls, pretrained_model_name_or_path, **kwargs)
281 if os.path.isdir(pretrained_model_name_or_path):
282 processor_class.register_for_auto_class()
--> 283 return processor_class.from_pretrained(
284 pretrained_model_name_or_path, trust_remote_code=trust_remote_code, **kwargs
285 )
286 elif processor_class is not None:
287 return processor_class.from_pretrained(
288 pretrained_model_name_or_path, trust_remote_code=trust_remote_code, **kwargs
289 )

File ~/anaconda3/envs/pytorch_p310/lib/python3.10/site-packages/transformers/processing_utils.py:226, in ProcessorMixin.from_pretrained(cls, pretrained_model_name_or_path, cache_dir, force_download, local_files_only, token, revision, **kwargs)
223 if token is not None:
224 kwargs["token"] = token
--> 226 args = cls._get_arguments_from_pretrained(pretrained_model_name_or_path, **kwargs)
227 return cls(*args)

File ~/anaconda3/envs/pytorch_p310/lib/python3.10/site-packages/transformers/processing_utils.py:270, in ProcessorMixin._get_arguments_from_pretrained(cls, pretrained_model_name_or_path, **kwargs)
267 else:
268 attribute_class = getattr(transformers_module, class_name)
--> 270 args.append(attribute_class.from_pretrained(pretrained_model_name_or_path, **kwargs))
271 return args

File ~/anaconda3/envs/pytorch_p310/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:723, in AutoTokenizer.from_pretrained(cls, pretrained_model_name_or_path, *inputs, **kwargs)
721 if os.path.isdir(pretrained_model_name_or_path):
722 tokenizer_class.register_for_auto_class()
--> 723 return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
724 elif config_tokenizer_class is not None:
725 tokenizer_class = None

File ~/anaconda3/envs/pytorch_p310/lib/python3.10/site-packages/transformers/tokenization_utils_base.py:1854, in PreTrainedTokenizerBase.from_pretrained(cls, pretrained_model_name_or_path, cache_dir, force_download, local_files_only, token, revision, *init_inputs, **kwargs)
1851 else:
1852 logger.info(f"loading file {file_path} from cache at {resolved_vocab_files[file_id]}")
-> 1854 return cls._from_pretrained(
1855 resolved_vocab_files,
1856 pretrained_model_name_or_path,
1857 init_configuration,
1858 *init_inputs,
1859 token=token,
1860 cache_dir=cache_dir,
1861 local_files_only=local_files_only,
1862 _commit_hash=commit_hash,
1863 _is_local=is_local,
1864 **kwargs,
1865 )

File ~/anaconda3/envs/pytorch_p310/lib/python3.10/site-packages/transformers/tokenization_utils_base.py:2017, in PreTrainedTokenizerBase._from_pretrained(cls, resolved_vocab_files, pretrained_model_name_or_path, init_configuration, token, cache_dir, local_files_only, _commit_hash, _is_local, *init_inputs, **kwargs)
2015 # Instantiate tokenizer.
2016 try:
-> 2017 tokenizer = cls(*init_inputs, **init_kwargs)
2018 except OSError:
2019 raise OSError(
2020 "Unable to load vocabulary from file. "
2021 "Please check that the provided vocabulary is accessible and not corrupted."
2022 )

File ~/.cache/huggingface/modules/transformers_modules/ydshieh/kosmos-2-patch14-224/d591f18e3ce08debe6bbdc7117b87a1595450179/tokenization_kosmos2_fast.py:140, in Kosmos2TokenizerFast.init(self, vocab_file, tokenizer_file, bos_token, eos_token, sep_token, cls_token, unk_token, pad_token, mask_token, num_patch_index_tokens, add_tag_and_patch_index_tokens, **kwargs)
126 super().init(
127 vocab_file,
128 tokenizer_file=tokenizer_file,
(...)
136 **kwargs,
137 )
139 self.vocab_file = vocab_file
--> 140 self.can_save_slow_tokenizer = False if not self.vocab_file else True
142 self.eod_token = ""
144 self.boi_token = ""

AttributeError: can't set attribute 'can_save_slow_tokenizer'