Shuming Ma
Shuming Ma
你好，当前版本针对lcsts 1.0。 处理数据时需要将数据集中的原始文本抽取出来放在train.src/valid.src文件里，将摘要抽取出来放在train.tgt/valid.tgt里，然后再用 python preprocess.py -train_src train.src -train_tgt train.tgt -valid_src valid.src -valid_tgt valid.tgt -save_data lcsts.pt 处理得到lcsts.pt文件。
Hi, thanks for reporting the issue. We are working on that. The codes will be updated once it is done.
> > ``` > > Hi, thanks for reporting the issue. We are working on that. The codes will be updated once it is done. > > ``` > >...
Running a 405B model on a single PC is super cool! And BitNet can definitely help that. Unfortunately, there is no plan for now due to the constrain of resources....