unilm Running the EdgeLM model on XSum

wfauudbj 于 2个月前发布在其他

关注(0)|答案(2)|浏览(33)

Hi I am trying to use the EdgeLM model and was wondering

how I can run the model with pre-trained weights in interactive mode, I'd like to run it for a summarization task.
I was also wondering if the pre-trained weights can be used to replicate the results reported on the XSum dataset.
How to make use of the pre-trained 2k vocab file and sentencepiece model while attempting 1 and 2.
How can I run the model on CPU only.

unilm

来源：https://github.com/microsoft/unilm/issues/835

2条答案

按热度按时间

6rvt4ljy1#

你好，
(1) 你可以尝试使用fairseq-interactive来以交互模式使用模型。
(2) 是的，但你需要为XSum微调模型。预训练权重不能直接用于摘要生成。
(3) 操作方式与说明中的相同，只需将fairseq-generate替换为fairseq-interactive(你可以参考fairseq-interactive查看详细说明)。
(4) 在运行fairseq-interactive时，需要添加标志--cpu。

赞(0）回复(0）举报 2个月前

cgvd09ve2#

你好，@getao,我想知道在摘要中使用什么任务来处理边缘生成器？

赞(0）回复(0）举报 2个月前