Anonymous
Anonymous
Dear Xuchen I'm interested in the ranker that contained in qa, but the code base is huge and has some other irrelevent items, how should I run the ranker directly...
I noticed that lr in code is 0.01 while paper is 0.05 with adagrad, and I tried with 0.05 to train the model but train loss doesn't decrease at all,...
I noticed that in **test** function of **trainer** module you write `output = output.data.squeeze().cpu()` Why you move `output` to cpu ? By the way in **SimilarityTreeLSTM** of **model** module `output...
From the hugging face [blog](https://huggingface.co/blog/starcoder) all code for data preprocessing will be released Where are these codes? Could you provide a link? Thanks!
Dear andersbll I installed the cuda and cuDNN correctlly   then I switched into cudarray directory ``` make sudo...
Dear authors of clang-8, I want to use clang-8 to fine tune the T5 model, however, I dont know what is the task prefix (e.g. for translation, the prefix could...
I noticed that auto scroll browser when preview has been brought in v1.2 but when I use `ctrl+Alt+o` in my test md file and edit in another place the browser...