Using GRPOTrainer with a custom PyTorch module?

[enyoukai]

Hello! I was wondering what changes I would need to make to use GRPOTrainer with a custom PyTorch module class.

Currently I have an nn.Module subclass that wraps around an existing Huggingface transformer, except with a custom forward and generate function.

I was wondering though if there were resources on either converting an nn.Module to a transformer to be used with Trainer, or what other functionality I would need to implement as well as changes I’d need to make to my forward and generate methods to work with

[John6666]

If you inherit PreTrainedModel, you should have most of the necessary functions. As for Trainer, it seems that you can modify loss functions, gradient-related functions, and so on.

What is difference between Model.register_for_auto_class and AutoModel.register?

I have created some new model and want to register it, so I can use AutoModelFor…() to call it. I have read Sharing custom models, but I can’t tell the difference between ResnetConfig.register_for_auto_class() ResnetModel.register_for_auto_class("AutoModel") ResnetModelForImageClassification.register_for_auto_class("AutoModelForImageClassification") and AutoConfig.register("resnet", ResnetConfig) AutoModel.register(ResnetConfig, ResnetModel) AutoModelForImageClassification.register(ResnetCon…

Adding a new model to Transformers