Integrating the Best of TF into PyTorch, for Machine Learning, Natural Language Processing, and Text Generation. This is part of the CASL project: http://casl-project.ai/
A error occurs when I run beam search decoder. And I think the error code should be line 490 in the picture.
I think the correct code for this operation is: topk_beam_index = topk_ids // vocab_size
A error occurs when I run beam search decoder. And I think the error code should be line 490 in the picture. I think the correct code for this operation is: topk_beam_index = topk_ids // vocab_size