Kexin Wang

Hi @liushenglei, thanks for your attention! Sorry for the late reply. I have just come back from my holiday:). @nreimers yes! I am also very interested in that and would...

> @kwang2049 @liushenglei @wduo Can you please keep me in the loop? I am also interested in the CN model. My email is [[email protected]](mailto:[email protected]). Can we connect? Thank you. Yeah,...

Hi @alsbhn, could you please tell me what you mean by "didn't work"? Do you mean the code was not runnable with this setting or something about the performance?

Thanks for pointing out this issue. I need some time to check what could be the exact reason. As I can imagine, there might be four potential reasons: (1) The...

Thanks for opening this issue! I will investigate this and have removed the link from the home page of this repo.

Hi @Matthieu-Tinycoaching, sorry for the delay. This issue is related to the dependencies of BeIR. Here I invite @NThakur20 to answer your question. But as a quick remedy, I think...

Thanks for reporting this issue. I found BeIR has just excluded tensorflow in requirements. This means in theory gpl could also work without it. I will dig into this issue...

The easiest solution would be to go with `nn.DataParallel`, although it might not be the most efficient way. Definitely, this will help for training with larger batches. I will have...

Hi @aqsa27, sorry for the delay. Could you please try this quick **toy** example: ```bash wget https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/fiqa.zip unzip fiqa.zip export dataset="fiqa" python -m gpl.train \ --path_to_generated_data "generated/$dataset" \ --base_ckpt "distilbert-base-uncased"...

Thanks for sharing your experience @ahadda5 and pointing out the misleading point! I will add some assertions about it to give hints and make it more clear.