requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/weights/icon_caption_florence/resolve/main/config.json

Hey guys, I'm trying to run the gradio_demo.py and demo.ipynb locally and it looks like the repository that the demo code relies on is no longer available.

Can you please fix this? Or let me know how to run it?

Thanks.

Error Message:

Repository Not Found for url: https://huggingface.co/weights/icon_caption_florence/resolve/main/config.json.
Please make sure you specified the correct `repo_id` and `repo_type`.
If you are trying to access a private or gated repo, make sure you are authenticated.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/Users/matthew/Desktop/omniparser/OmniParser/gradio_demo.py", line 16, in <module>
    caption_model_processor = get_caption_model_processor(model_name="florence2", model_name_or_path="weights/icon_caption_florence")
                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/matthew/Desktop/omniparser/OmniParser/utils.py", line 54, in get_caption_model_processor
    model = AutoModelForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.float32, trust_remote_code=True)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/matthew/Desktop/omniparser/OmniParser/venv/lib/python3.11/site-packages/transformers/models/auto/auto_factory.py", line 487, in from_pretrained
    resolved_config_file = cached_file(
                           ^^^^^^^^^^^^
  File "/Users/matthew/Desktop/omniparser/OmniParser/venv/lib/python3.11/site-packages/transformers/utils/hub.py", line 426, in cached_file
    raise EnvironmentError(
OSError: weights/icon_caption_florence is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'

Start with gradio_demo.py and demo.ipynb, then inspect get_caption_model_processor in utils.py where weights/icon_caption_florence is passed to the model loader. Reproduce the 404 and trace how the model path is resolved. Done means both referenced demos can load the caption model without the reported missing-repository error, or clearly document the required run instructions.