Yuanfang Peng

Hi, @Twilightaaa ! Could you please share your reproduction script of experiments on location 9 of the NQ dataset? Thanks!

Hi, Dear author, but what if we have different time slices in each columns originally. For example, a_t_0,b_t_0,c_t_0,a_t_1,b_t_1,c_t_1

Hi Jerzy, thanks much for sharing this. Actually I'm trying to build structure learning algorithm for hybrid DBN and I found this repo has implemented this. But it was implemented...

Hi @jrzkaminski ! Thanks so much for your prompt reply. Your suggestion is really helpful to me and look forward to your project. By the way, I also found that...

Hi @Evelyn697 , thanks for reaching out. Actually I directly use a Dynamic Gaussian Bayesian network for my project, as implementing a hybrid DBN is too complex using current open-source...

Hi @njzxj , have you fixed this problem? I also encountered this problem when finetuning wna2.1-t2v-1.3b on my own dataset. When I set lora_alpha to 1, the results are not...

Hi @njzxj , thanks for your prompt reply. By the way, does "reasonableness of the prompt words" means that the prompt should be aligned with the video. Could you please...

Thanks so much for your prompt reply, Jacob. pomegranate is already a powerful library. But if you know any other library that support continuous and discrete variables simultaneously in DBN,...

Hi, I also found that only if I load model to a single GPU, the CLI inference and the "get start code" can run successfully. I guess this transcript only...

Hi, I found that using a single GPU for inference can solve this problem, then also change your cuda version to 1.8