close
The Wayback Machine - https://web.archive.org/web/20201001211339/https://github.com/huggingface/transformers/issues
Skip to content

/ transformers

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.

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

505 Open 3,993 Closed
505 Open 3,993 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels.
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀
Training loss suddenly increases and stays the same
#7524 opened Oct 1, 2020 by gungor2
MultiGPU Trainer: each processes uses more memory than 1 GPU job Distributed Training / Models
#7520 opened Oct 1, 2020 by sshleifer
2
XLNet finetuning
#7519 opened Oct 1, 2020 by alshahrani2030
Overflow error: Can't convert negative value to unsigned it [RAG Model]
#7517 opened Oct 1, 2020 by sashank06 2 of 2
6
[Longformer] Output both local attentions and global attentions when `output_attentions=True` -> Good Second Issue Good Second Issue
#7514 opened Oct 1, 2020 by patrickvonplaten
@patrickvonplaten
[XLNet] attention_mask / input_mask - Why two `attention_mask` inputs?
#7512 opened Oct 1, 2020 by patrickvonplaten
@patrickvonplaten @LysandreJik @sgugger
2
[Transfo-XL] Impossible to pass `attention_mask` to model
#7511 opened Oct 1, 2020 by patrickvonplaten
@patrickvonplaten @TevenLeScao
@LysandreJik @sgugger
[Reformer, Longformer, Roberta, GPT2, CTRL] attention_mask should be at second argument
#7510 opened Oct 1, 2020 by patrickvonplaten
@patrickvonplaten @LysandreJik @sgugger
Turning the SQuAD dataset class into an iterator to save ram and redistribute time
#7503 opened Oct 1, 2020 by mariusjohan
Functionality to pass first few tokens as input to the decoder in T5 model
#7502 opened Oct 1, 2020 by ayushtiku5
Trucated Outputs while finetuning 'bart-base' on XSUM [Summarization Task]
#7500 opened Oct 1, 2020 by yashgupta-7
How to generate data using beam search from a custom gpt2 model?
#7497 opened Oct 1, 2020 by nrjvarshney
3
BertforSequenceClassification MSELoss() without normalizing using sigmoid/softmax
#7496 opened Oct 1, 2020 by liusiyi641
quick questions about the `BertModelLMHeadModel`.
#7495 opened Oct 1, 2020 by h56cho
Is the multiple-choice head for the pre-trained `LongformerForMultipleChoice` model pre-trained?
#7494 opened Oct 1, 2020 by h56cho
`run_squad_trainer` doesn't actually use a Rust tokenizer + errors in `squad_convert_example_to_features` when using a Rust tokenizer
#7492 opened Sep 30, 2020 by k8si 3 of 4
Use of global attention of Longformer when generating
#7489 opened Sep 30, 2020 by alexyalunin
1
Using BERT for spelling correction
#7486 opened Sep 30, 2020 by naturecreator
Tenosrflow Loading the saved Model For GPT2
#7485 opened Sep 30, 2020 by santhoshkolloju
3
Upload models using transformers-cli fails
#7480 opened Sep 30, 2020 by agemagician 2 of 4
@patrickvonplaten
4
Loading saved model not working
#7479 opened Sep 30, 2020 by irocks04
3
RAG: Can we have a document that explains the fine-tuning mechanism?
#7476 opened Sep 30, 2020 by shamanez
1
Seq2SeqTrainer: add a fast test that doesn't learn anything but can run on CPU
#7466 opened Sep 30, 2020 by sshleifer
1
RAG - reproducing RAG-Sequence QA score
#7465 opened Sep 30, 2020 by acslk
@patrickvonplaten @lhoestq
3
RAG - how to precompute custom document index?
#7462 opened Sep 29, 2020 by aced125
4
ProTip! Exclude everything labeled bug with -label:bug.
You can’t perform that action at this time.