kkelev
kkelev
thanks , this helped me a lot @gmryu
> I think the simplest method for this is to split your data into several shards and translate them with multiple works in a parallel way. I only have one...
> Hi @kkeleve, may I ask did you do any preprocessing with the data before generating the back translation pairs, like fairseq-generate command, and if so, could you please share...
> Hi thanks. Gao Peng emailed me yesterday and shared with me his commands. > > ``` > srun --gres gpu:1 fairseq-generate data-bin/wmt16_en_de_bpe32k --path checkpoint.avg20.pt --beam 4 --lenpen 0.6 --gen-subset...
you can try it `export PYTHONPATH=$PYTHONPATH:/root/fairseq/`
@[gmryu](https://github.com/gmryu) Hi, forgive me for not making it clear. The above picture is the loss figureof the student model, and I did not save the loss figure of the teacher...
Hi, @[gmryu](https://github.com/gmryu) thanks for your reply . I should belong to 2 . I use an autoregressive model as a teacher to distill the original knowledge, and I want to...
> 你好 请问你现在是否弄清楚了label的意义，我想对翻译任务的单语言语料进行增强，没有像分类任务的label，标签随便设置可以吗
> NLTK tree can you tell me how to use NLTK tree transform in stanza?please
> > I'm experiencing the following error when I run the generate.sh script: > > No such file or directory: './data/test.m2' > > Is this file missing or should I...