Baizhou Huang

Multiple nodes training

2

1. Add Multi_Node_Training in image_classification. 2. Write a tutorial about multi-node training in README.md 3. Use ViT model as an example.

Questions about email dataset

1

Thanks for the awesome work!!! I have several questions about the email dataset in data_processed/email/vanilla 1. what's the difference between email.newsumms and the normal data (such as train.source) 2. Does...

About loss in training_losses_seq2seq() when time step t=0

5

Thanks for your great work. I have a question about loss calculation in training_losses_seq2seq() when the sampled time step `t=0` https://github.com/Shark-NLP/DiffuSeq/blob/bdc8f0adbff22e88c8530d1f20c3c7589c061d40/diffuseq/gaussian_diffusion.py#L612-L619 If `t=0`. The `x_t = self.q_sample()` line is incorrect,...

Pretrained Weights of Differential Transformers

2

Thanks for the great work! Do you plan to release your pretrained weights on Hugging Face? It would be a significant contribution to the community.