File size: 571 Bytes
57bdca5 |
1 2 3 4 5 6 7 8 9 10 11 12 |
Since our model is just a wrapper around it, it's going to be
easy to transfer those weights:
import timm
pretrained_model = timm.create_model("resnet50d", pretrained=True)
resnet50d.model.load_state_dict(pretrained_model.state_dict())
Now let's see how to make sure that when we do [~PreTrainedModel.save_pretrained] or [~PreTrainedModel.push_to_hub], the
code of the model is saved.
Registering a model with custom code to the auto classes
If you are writing a library that extends 🤗 Transformers, you may want to extend the auto classes to include your own
model. |