def create_and_check_for_causal_lm(
     self,
     config,
     input_ids,
     token_type_ids,
     input_mask,
     sequence_labels,
     token_labels,
     choice_labels,
     encoder_hidden_states,
     encoder_attention_mask,
 ):
     model = RoFormerForCausalLM(config=config)
     model.to(torch_device)
     model.eval()
     result = model(input_ids,
                    attention_mask=input_mask,
                    token_type_ids=token_type_ids,
                    labels=token_labels)
     self.parent.assertEqual(
         result.logits.shape,
         (self.batch_size, self.seq_length, self.vocab_size))
    def create_and_check_decoder_model_past_large_inputs(
        self,
        config,
        input_ids,
        token_type_ids,
        input_mask,
        sequence_labels,
        token_labels,
        choice_labels,
        encoder_hidden_states,
        encoder_attention_mask,
    ):
        config.is_decoder = True
        config.add_cross_attention = True
        model = RoFormerForCausalLM(config=config)
        model.to(torch_device)
        model.eval()

        # first forward pass
        outputs = model(
            input_ids,
            attention_mask=input_mask,
            encoder_hidden_states=encoder_hidden_states,
            encoder_attention_mask=encoder_attention_mask,
            use_cache=True,
        )
        past_key_values = outputs.past_key_values

        # create hypothetical multiple next token and extent to next_input_ids
        next_tokens = ids_tensor((self.batch_size, 3), config.vocab_size)
        next_mask = ids_tensor((self.batch_size, 3), vocab_size=2)

        # append to next input_ids and
        next_input_ids = torch.cat([input_ids, next_tokens], dim=-1)
        next_attention_mask = torch.cat([input_mask, next_mask], dim=-1)

        output_from_no_past = model(
            next_input_ids,
            attention_mask=next_attention_mask,
            encoder_hidden_states=encoder_hidden_states,
            encoder_attention_mask=encoder_attention_mask,
            output_hidden_states=True,
        )["hidden_states"][0]
        output_from_past = model(
            next_tokens,
            attention_mask=next_attention_mask,
            encoder_hidden_states=encoder_hidden_states,
            encoder_attention_mask=encoder_attention_mask,
            past_key_values=past_key_values,
            output_hidden_states=True,
        )["hidden_states"][0]

        # select random slice
        random_slice_idx = ids_tensor((1, ), output_from_past.shape[-1]).item()
        output_from_no_past_slice = output_from_no_past[:, -3:,
                                                        random_slice_idx].detach(
                                                        )
        output_from_past_slice = output_from_past[:, :,
                                                  random_slice_idx].detach()

        self.parent.assertTrue(
            output_from_past_slice.shape[1] == next_tokens.shape[1])

        # test that outputs are equal for slice
        self.parent.assertTrue(
            torch.allclose(output_from_past_slice,
                           output_from_no_past_slice,
                           atol=1e-3))