| The line that sets the config_class is not mandatory, unless | |
| you want to register your model with the auto classes (see last section). | |
| If your model is very similar to a model inside the library, you can re-use the same configuration as this model. | |
| You can have your model return anything you want, but returning a dictionary like we did for | |
| ResnetModelForImageClassification, with the loss included when labels are passed, will make your model directly | |
| usable inside the [Trainer] class. |