tates.numpy(), return_tensors="tf")
        >>> doc_scores = tf.squeeze(
        ...     tf.matmul(
        ...         tf.expand_dims(question_hidden_states, axis=1), docs_dict["retrieved_doc_embeds"], transpose_b=True
        ...     ),
        ...     axis=1,
        ... )
        >>> # 3. Forward to generator
        >>> outputs = model(
        ...     inputs=None,
        ...     context_input_ids=docs_dict["context_input_ids"],
        ...     context_attention_mask=docs_dict["context_attention_mask"],
        ...     doc_scores=doc_scores,
        ...     decoder_input_ids=input_dict["labels"],
        ... )

        >>> # or directly generate
        >>> generated = model.generate(
        ...     context_input_ids=docs_dict["context_input_ids"],
        ...     context_attention_mask=docs_dict["context_attention_mask"],
        ...     doc_scores=doc_scores,
        ... )
        >>> generated_string = tokenizer.batch_decode(generated, skip_special_tokens=True)
        ```r„