huggingface / transformers

Watch 666
Star 33.9k
Fork 8.1k

Code
Issues 494
Pull requests 114
Actions
Projects 15
Security
Insights

Code
Issues
Pull requests
Actions
Projects
Security
Insights

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.

Pick a username

Email Address

Password

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

494 Open 3,887 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

[Bug/Question] Write With Transformers Implementation vs. Custom Implementation

#7273 opened Sep 20, 2020 by krrishdholakia

Distilbert classification

#7271 opened Sep 20, 2020 by akald

Multitask pre-training setting

#7270 opened Sep 20, 2020 by antoniomastro1996

LXMERT pre-training tasks

#7266 opened Sep 20, 2020 by LetiP

Does Longformer support 3d attention mask ?

#7265 opened Sep 20, 2020 by Maybewuss

Changing learning rate for BertModelforTokenClassification

#7264 opened Sep 20, 2020 by YojanaGadiya

When I updated my transformers to the latest, the previously trained model loaded with an error

#7262 opened Sep 20, 2020 by wulaoshi 0 of 4

LXMERT visual feature extraction during training/fine-tuning phase

#7261 opened Sep 20, 2020 by mmiakashs

A confusion about mrc model

#7260 opened Sep 20, 2020 by Maybewuss

[save/load model] authorized keys, no save keys, etc.

#7258 opened Sep 19, 2020 by stas00

[fsmt] Expanding Positional Embeddings fsmt

#7256 opened Sep 19, 2020 by stas00

[testing] when to @slow and when not to? (huge models download)

#7250 opened Sep 19, 2020 by stas00

very poor performance of Longformer on SQuAD-like question-answering tasks

#7249 opened Sep 19, 2020 by xixiaoyao 2 of 4

[example/glue] run_glue compute metrics fail for bart like models

#7247 opened Sep 19, 2020 by patil-suraj

How to get cross attention weights of decoder when using 'encoderdecodermodel'

#7246 opened Sep 19, 2020 by kimmo1019

distributed_eval edge case

#7245 opened Sep 19, 2020 by sshleifer

TypeError: 'ByteLevelBPETokenizer' object is not callable

#7234 opened Sep 18, 2020 by yadavpp

trainer.evaluate() aggregates predictions on GPU and causes CUDA out of memory issues for large datasets

#7232 opened Sep 18, 2020 by eugeneware 2 of 4

test fsmt finetuning fsmt

#7230 opened Sep 18, 2020 by sshleifer

a possible hack for FSMT's SinusoidalPositionalEmbedding peculiarity

#7229 opened Sep 18, 2020 by stas00

FSMT Training scripts

#7228 opened Sep 18, 2020 by wangyong1122

tokenizer.add_tokens conflict with MBart's tokenizer

#7222 opened Sep 17, 2020 by znculee

[model cards] yaml specs and related questions

#7208 opened Sep 17, 2020 by stas00

[models website] search UI issues

#7206 opened Sep 17, 2020 by stas00

[s2s] reload dataloaders every epoch?

#7203 opened Sep 17, 2020 by sshleifer

Previous 1 2 3 4 5 … 19 20 Next

Previous Next

ProTip! Find all open issues with in progress development work with linked:pr.