Haotian Cui
Haotian Cui
Thank you for the nice suggestion. I will try to set it up next week. In the meantime, are you using `flash-attn
@shenyeyouyi Thank you. I agree that `nvcc -V` should tell the current visible cuda version, especially when you have multiple cuda versions installed.
Hi, @bzip2 , you don't necessarily need the Nvidia PyTorch container. You do need pytroch, cuda, and a compatible GPU before installing flash-attn. So can you please share those details?
Hi @alexaibio, thank you so much for the efforts! Upon reflection, I propose an alternative approach: what if we include a hyperlink in our project's README directing users to your...
Hi @nmahieu-empresstx, Thanks! I am trying to understand the question you provided. Could you further explain the figure you drew here?
Hi @nmahieu-empresstx , thank you for the explanation. I think to answer your questions, let me first explain the rationale for the reverse perturbation task. The ultimate goal for this...
Hi @kzkedzierska thank you for your interest! In general, anything listed in that `args.json` within the pretraining model folder is about the setting during pre-training. I find we haven't made...
Hi, thank you for the suggestion! We have uploaded the links for the datasets. Please have a look at https://github.com/bowang-lab/scGPT/blob/main/data/README.md Currently, some of these datasets are processed by the original...
Hi thanks for the question. Which application do you mean specifically?
Sorry for the waiting, will try to put it out by Thursday, Sept. 21.