Skip to content

Issues: gordicaleksa/pytorch-original-transformer

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

9 Open 0 Closed
9 Open 0 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

A environment problem
#10 opened Mar 19, 2024 by BruceWang01
torchtext.data import not working in the latest versions of pytorch.
#9 opened Jan 15, 2024 by shreyashkar-ml
Sorry, but I couldn't understand where is the concatenation layer after the multi head self attention, shouldn't there be?
#8 opened Dec 13, 2023 by Domics10
sharing weight matrix between the two embedding layers and the pre-softmax linear transformation
#7 opened Jan 19, 2022 by nataly-obr
Error when running "python training_script.py --batch_size 100 --dataset_name IWSLT --language_direction G2E
#6 opened Nov 29, 2021 by minertom
2
Frequency in the positional encodings
#5 opened Jul 23, 2021 by FAhtisham
issue when command :python training_script.py --batchsize 2 -- dataset_name IWSLT --language_direction G2E
#4 opened Apr 13, 2021 by adamas-v
2
Issue regarding "9.1 Download pretrained transformers automatically"
#3 opened Apr 2, 2021 by CaterinaFabbri
2
can you show the bleu for this repo on WMT14 dataset?
#2 opened Jan 29, 2021 by GuangyanZhang
ProTip! Add no:assignee to see everything that’s not assigned.