Integrate with huggingface

[not-lain]

this pr will mainly add 3 methods to michelangelo

• save_pretrained
• push_to_hub
• from_pretrained: initialize and load the model weights

allowing your models to be easily integrated with huggingface using the PyTorchModelHubMixin class, I made this notebook https://colab.research.google.com/drive/1rStTsfAqoT7wXijt4a2wPbd6ZUYG3jTc?usp=sharing explaining how to migrate your weights
by the end of the notebook, all users can load your model simply by

!!pip install -qU git+https://github.com/not-lain/Michelangelo.git@integrate-with-huggingface # or your main branch when this is merged
# no more renitializing the model and manually downloading the weights

from michelangelo.models.asl_diffusion.clip_asl_diffuser_pl_module import ClipASLDiffuser
# will instantiate the model and load the weights automatically
new_model = ClipASLDiffuser.from_pretrained("not-lain/Michelangelo")

Why you should integrate your model with huggingface ?

• easily save, load and push your model
• Keep track on how many times your model has been downloaded by the community (download metrics will be enabled again)
• Automatic model card generation: the metadata in the card allows you to filter your searches easily to check how many michelangelo models exist on the Hub.
• Recommended: after this pr is merged we can open a pull request on this file to make the "michelangelo" library official on the Hub meaning better discoverability + possibility to add code snippets.

do not hesitate if you have any reviews on the pr or any questions.

Kind regards,
Hafedh Hichri