Input shape: Batch x Time x Channel attention_mask: [bsz, q_len]

Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mask (

r""" Args: labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): Labels for computing

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression

r""" start_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for position (index) of the start of the la

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression

Returns vocab as a dict

Save the vocabulary and special tokens file to a directory. Args: save_directory (`str`): The directory