Zekun Li
Zekun Li
> Thank you for your reply! There is no OOM problem. I have filled zeros for position embedding and transformed the model to hdf5 format successfully. But when I tried...
> @Leezekun I think only changes of the export script are needed to support GPT-J if the model structures are the same and only variable names are different. BTW, Can...
@Taka152 I will appreciate it if you can help me with that! Thanks!
@Taka152 Hi, can you help me with that? Thanks so much! Besides, I don't know how to join your organization to reach you. It said I needed a invite code.
Hi, thanks for the reply. Did you mean that the comparison results between your model and other models are all trained and evaluated on delexicalized response (Table 4 and 5)?...
Have you installed the transformers package?
The tokenizer is just for analyzing the length of static features. It is not necessary. You can remove the code related to the tokenizer if you have trouble loading it.
Sorry for the late reply. This should be the download link: http://www.timeseriesclassification.com/aeon-toolkit/Archives/Multivariate2018_ts.zip.
Hi, Thank you for your patience and for showing interest in our work. You can locate the code that we've developed to convert data into line graph images with matplotlib...
Hi, we have recently updated the codebase and have included the generated images to facilitate your code execution. To obtain the necessary files and follow the instructions, please refer to...