!!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.
this pr will mainly add 3 methods to michelangelo
save_pretrained
push_to_hub
from_pretrained
: initialize and load the model weightsallowing 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
Why you should integrate your model with huggingface ?
do not hesitate if you have any reviews on the pr or any questions.
Kind regards, Hafedh Hichri