I am working on a project that involves a custom video model, and I need to set it up and run it on my server. The model requires specific configuration files, such as config.json, and weights in formats like pytorch_model.bin and pytorch_model.safetensors.

I have the following directory structure for my model files:

/model_directory
├── encoder
│   ├── config.json
│   └── pytorch_model.safetensors
├── controlnet
│   ├── config.json
│   └── pytorch_model.safetensors
└── attention
    └── attention.ckpt

Could someone provide a detailed example or guide on how to:

Properly load these models and their configurations.
I get this error currently on huggingface.

OSError: /repository does not appear to have a file named config.json. Checkout 'https://huggingface.co//repository/None' for available files.

Set up an inference pipeline to run the model.
Handle potential issues such as missing configuration files or incorrect paths.
Any help or examples would be greatly appreciated!

Thank you!