UFDAdaptorGlobalModel

class UFDAdaptorGlobalModel(config)

The UFD Adaptor Global Model used for unsupervised training for global context.

This method inherits from UFDAdaptorGlobalPreTrainedModel for weights initalization and utility functions from transformer PreTrainedModel class.

Parameters

config (UFDAdaptorGlobalConfig) – Model configuration class with all parameters required for the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Use the from_pretrained method to load the model weights.

forward(input: torch.FloatTensor) → Tuple[torch.FloatTensor, torch.FloatTensor]

Parameters

( (input) – ob:’torch.FloatTensor’ of shape :obj:’(batch_size, max_num_words)’: Word IDs of text