Main_input_name ( str) - The name of the principal input to the model (often input_ids for NLP Is_parallelizable ( bool) - A flag indicating whether this model supports model parallelization. path ( str) - A path to the TensorFlow checkpoint.īase_model_prefix ( str) - A string indicating the attribute associated to the base model in derivedĬlasses of the same architecture adding modules on top of the base model.config ( PreTrainedConfig) - An instance of the configuration associated to the model.model ( PreTrainedModel) - An instance of the model on which to load the TensorFlow checkpoint.Load_tf_weights ( Callable) - A python method for loading a TensorFlow checkpoint in a PyTorch model, prune heads in the self-attention heads.Ĭlass attributes (overridden by derived classes):Ĭonfig_class ( PretrainedConfig) - A subclass of PretrainedConfig to use as configuration class. ![]() ![]() PreTrainedModel takes care of storing the configuration of the models and handles methods for loading,ĭownloading and saving models as well as a few methods common to all models to:
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |