Fred

I think it is “train_num_steps“.

had the same problem.... Any solutions? @jiaweizzhao

我还有个问题。你真的好厉害能学完这么多门课，你是怎么找出这么多时间来的。我光是做一个lab就得花五六个小时。。

I am not the author. Based on my understanding, the authors propose an algorithm that leverages the discriminative ability of existing diffusion models for classification tasks. That means the performance...

Yes! You did a great job on this paper. I am just curious about how effective the log-likelihood estimation could be since song claimed that the exact log-likelihood is SOTA....

Thanks!!! That's a good paper. My takeaways are that it might be necessary to increase the hidden dim for the model to memorize the prev tokens when sequences get longer.

I am gonna leave this issue open for discussion of the paper.

hi there! I am open to collaboration on interesting works. You may want to discuss your ideas and implementation details with me? best, zhangzhi

hi, the training is pretty cheap. I can fit the model in a 10g GPU. Regarding the documentation, please follow the readme to install pkgs and train the model. Please...

Hi, - I don't have discord, sorry. - I have not tested the code on 8g gpus. By reducing the batch size, the memory consumption would be reduced to fit...