How to download the model to my computer for use without an internet connection?

[NguyenDucQuan12]

I'm using PaddleOCR to read text from PDFs and images, with the content in Vietnamese. I want the model to be loaded into a specified folder, and then used in my own folder for subsequent uses.
I'm using the following code.

from paddleocr import PPStructureV3

input_file = "assets\Sodat2.pdf"
pipeline = PPStructureV3(
    # models
    text_recognition_model_name="models/PP-OCRv5_server_rec",
    text_detection_model_name="models/PP-OCRv5_server_det",
    formula_recognition_model_name="models/PP-FormulaNet_plus-L", 
    layout_detection_model_name="models/PP-DocLayout_plus-L",
    region_detection_model_name="models/PP-DocBlockLayout",
    # model dirs
    text_recognition_model_dir='models/PP-OCRv5_server_rec',
    text_detection_model_dir='models/PP-OCRv5_server_det',
    formula_recognition_model_dir='models/PP-OCRv5_mobile_rec',
    layout_detection_model_dir='models/PP-DocLayout_plus-L',
    region_detection_model_dir='models/PP-DocBlockLayout',
    # Use options
    use_seal_recognition=False,
    use_table_recognition=False,
    use_chart_recognition=False,
    device="gpu",  # Use device to specify GPU for model inference
)
output = pipeline.predict(input=input_file)

for res in output:
    res.print() # Print the structured prediction output
    res.save_to_json(save_path="output") ## Save the current image's structured result in JSON format
    res.save_to_markdown(save_path="output")

However, I encountered an error:

(.venv_vlm) PS D:\Project\PaddleOCR> python src\test\test.py
Checking connectivity to the model hosters, this may take a while. To bypass this check, set `DISABLE_MODEL_SOURCE_CHECK` to `True`.
Creating model: ('PP-LCNet_x1_0_doc_ori', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: `C:\Users\Server_Quan_IT\.paddlex\official_models\PP-LCNet_x1_0_doc_ori`.
INFO: Could not find files for the given pattern(s).
D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddle\utils\cpp_extension\extension_utils.py:718: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md
  warnings.warn(warning_message)
WARNING: Logging before InitGoogleLogging() is written to STDERR
W1227 11:15:10.094090  2900 gpu_resources.cc:114] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 12.8, Runtime API Version: 11.8
Creating model: ('UVDoc', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: `C:\Users\Server_Quan_IT\.paddlex\official_models\UVDoc`.
Creating model: ('models/PP-DocBlockLayout', 'models/PP-DocBlockLayout')
Traceback (most recent call last):
  File "D:\Project\PaddleOCR\src\test\test.py", line 4, in <module>
    pipeline = PPStructureV3(
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\pp_structurev3.py", line 137, in __init__
Model files already exist. Using cached files. To redownload, please delete the directory manually: `C:\Users\Server_Quan_IT\.paddlex\official_models\PP-LCNet_x1_0_doc_ori`.
INFO: Could not find files for the given pattern(s).
D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddle\utils\cpp_extension\extension_utils.py:718: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md
  warnings.warn(warning_message)
WARNING: Logging before InitGoogleLogging() is written to STDERR
W1227 11:15:10.094090  2900 gpu_resources.cc:114] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 12.8, Runtime API Version: 11.8
Creating model: ('UVDoc', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: `C:\Users\Server_Quan_IT\.paddlex\official_models\UVDoc`.
Creating model: ('models/PP-DocBlockLayout', 'models/PP-DocBlockLayout')
Traceback (most recent call last):
  File "D:\Project\PaddleOCR\src\test\test.py", line 4, in <module>
    pipeline = PPStructureV3(
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\pp_structurev3.py", line 137, in __init__
D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddle\utils\cpp_extension\extension_utils.py:718: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md
  warnings.warn(warning_message)
WARNING: Logging before InitGoogleLogging() is written to STDERR
W1227 11:15:10.094090  2900 gpu_resources.cc:114] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 12.8, Runtime API Version: 11.8
Creating model: ('UVDoc', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: `C:\Users\Server_Quan_IT\.paddlex\official_models\UVDoc`.
Creating model: ('models/PP-DocBlockLayout', 'models/PP-DocBlockLayout')
Traceback (most recent call last):
  File "D:\Project\PaddleOCR\src\test\test.py", line 4, in <module>
    pipeline = PPStructureV3(
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\pp_structurev3.py", line 137, in __init__
download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md
  warnings.warn(warning_message)
WARNING: Logging before InitGoogleLogging() is written to STDERR
W1227 11:15:10.094090  2900 gpu_resources.cc:114] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 12.8, Runtime API Version: 11.8
Creating model: ('UVDoc', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: `C:\Users\Server_Quan_IT\.paddlex\official_models\UVDoc`.
Creating model: ('models/PP-DocBlockLayout', 'models/PP-DocBlockLayout')
Traceback (most recent call last):
  File "D:\Project\PaddleOCR\src\test\test.py", line 4, in <module>
    pipeline = PPStructureV3(
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\pp_structurev3.py", line 137, in __init__
WARNING: Logging before InitGoogleLogging() is written to STDERR
W1227 11:15:10.094090  2900 gpu_resources.cc:114] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 12.8, Runtime API Version: 11.8
Creating model: ('UVDoc', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: `C:\Users\Server_Quan_IT\.paddlex\official_models\UVDoc`.
Creating model: ('models/PP-DocBlockLayout', 'models/PP-DocBlockLayout')
Traceback (most recent call last):
  File "D:\Project\PaddleOCR\src\test\test.py", line 4, in <module>
    pipeline = PPStructureV3(
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\pp_structurev3.py", line 137, in __init__
W1227 11:15:10.094090  2900 gpu_resources.cc:114] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 12.8, Runtime API Version: 11.8
Creating model: ('UVDoc', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: `C:\Users\Server_Quan_IT\.paddlex\official_models\UVDoc`.
Creating model: ('models/PP-DocBlockLayout', 'models/PP-DocBlockLayout')
Traceback (most recent call last):
  File "D:\Project\PaddleOCR\src\test\test.py", line 4, in <module>
    pipeline = PPStructureV3(
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\pp_structurev3.py", line 137, in __init__
Model files already exist. Using cached files. To redownload, please delete the directory manually: `C:\Users\Server_Quan_IT\.paddlex\official_models\UVDoc`.
Creating model: ('models/PP-DocBlockLayout', 'models/PP-DocBlockLayout')
Traceback (most recent call last):
  File "D:\Project\PaddleOCR\src\test\test.py", line 4, in <module>
    pipeline = PPStructureV3(
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\pp_structurev3.py", line 137, in __init__
Creating model: ('models/PP-DocBlockLayout', 'models/PP-DocBlockLayout')
Traceback (most recent call last):
  File "D:\Project\PaddleOCR\src\test\test.py", line 4, in <module>
    pipeline = PPStructureV3(
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\pp_structurev3.py", line 137, in __init__
    super().__init__(**kwargs)
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\base.py", line 67, in __init__
Traceback (most recent call last):
  File "D:\Project\PaddleOCR\src\test\test.py", line 4, in <module>
    pipeline = PPStructureV3(
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\pp_structurev3.py", line 137, in __init__
    super().__init__(**kwargs)
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\base.py", line 67, in __init__
    pipeline = PPStructureV3(
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\pp_structurev3.py", line 137, in __init__
    super().__init__(**kwargs)
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\base.py", line 67, in __init__
    self.paddlex_pipeline = self._create_paddlex_pipeline()
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\base.py", line 105, in _create_paddlex_pipeline
    super().__init__(**kwargs)
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\base.py", line 67, in __init__
    self.paddlex_pipeline = self._create_paddlex_pipeline()
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\base.py", line 105, in _create_paddlex_pipeline
    self.paddlex_pipeline = self._create_paddlex_pipeline()
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddleocr\_pipelines\base.py", line 105, in _create_paddlex_pipeline
    return create_pipeline(config=self._merged_paddlex_config, **kwargs)
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddlex\inference\pipelines\__init__.py", line 167, in create_pipeline
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddlex\inference\pipelines\__init__.py", line 167, in create_pipeline
    pipeline = BasePipeline.get(pipeline_name)(
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddlex\utils\deps.py", line 206, in _wrapper
    pipeline = BasePipeline.get(pipeline_name)(
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddlex\utils\deps.py", line 206, in _wrapper
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddlex\utils\deps.py", line 206, in _wrapper
    return old_init_func(self, *args, **kwargs)
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddlex\inference\pipelines\_parallel.py", line 103, in __init__
    self._pipeline = self._create_internal_pipeline(config, self.device)
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddlex\inference\pipelines\_parallel.py", line 158, in _create_internal_pipeline
    return self._pipeline_cls(
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddlex\inference\pipelines\layout_parsing\pipeline_v2.py", line 84, in __init__
    self.inintial_predictor(config)
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddlex\inference\pipelines\layout_parsing\pipeline_v2.py", line 144, in inintial_predictor
    self.region_detection_model = self.create_model(
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddlex\inference\pipelines\base.py", line 106, in create_model
    model = create_predictor(
  File "D:\Project\PaddleOCR\.venv_vlm\lib\site-packages\paddlex\inference\models\__init__.py", line 75, in create_predictor
    assert Path(model_dir).exists(), f"{model_dir} is not exists!"
AssertionError: models/PP-DocBlockLayout is not exists!

What should I do, and how can I use the same method with the paddleOCRVL model?