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

480 Open 4,532 Closed
480 Open 4,532 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
👍 👎 😄 🎉 😕 ❤️ 🚀 👀
TFBertModel not working at all with any type of model
#8538 opened Nov 14, 2020 by bp91 2 of 4
Add a new model ConvBert New model
#8537 opened Nov 14, 2020 by RyanHuangNLP 3 of 3
Pretrain PEGASUS from scratch
#8536 opened Nov 14, 2020 by EKebriaei
mBart prefix and suffix for language id
#8534 opened Nov 14, 2020 by RQuispeC
Bertabs example: index_select(): Expected dtype int64 for index
#8533 opened Nov 13, 2020 by TheTimKiely
converting tensorflow checkpoint to pytorch
#8532 opened Nov 13, 2020 by mchari
[models website: files section] various issues/suggestions for a better UI
#8531 opened Nov 13, 2020 by stas00 1 of 5
2
Problem while pretraining MLM from scratch using Transformers
#8526 opened Nov 13, 2020 by meysamgh
1
LayoutLM Token Classification not learning
#8524 opened Nov 13, 2020 by AntPeixe
Reformer model crashes during casual LM evaluation
#8523 opened Nov 13, 2020 by qbeer
1
MLflowCallback to log run_name argument
#8519 opened Nov 13, 2020 by HenryMaguire
@sgugger
1
How to pretrain the model (like Roberta) again?
#8514 opened Nov 13, 2020 by drxmy
2
Finetune TFBertForMaskedLM model.fit() ValueError
#8510 opened Nov 13, 2020 by MarsSu0618
2
TPU issue: possible memory leak in eval loop
#8508 opened Nov 12, 2020 by zcain117 2 of 4
5
Fill-mask pipeline removes space after token prediction when loading pre-training model based on roberta-base
#8507 opened Nov 12, 2020 by ironflood 2 of 2
Unexpected behavior when using PubMedBERT with AutoModelForMaskedLM
#8505 opened Nov 12, 2020 by rahuln
Training the TFGPT2LMHeadModel with model.fit produces error
#8503 opened Nov 12, 2020 by bjourne
@jplu
3
TF T5-small with output hidden state and attention not owrking
#8502 opened Nov 12, 2020 by pathikchamaria
5
Why is the XLM-RoBERTa sometimes producing a standalone start of the word character (the special underscore with ord = 9601)
#8501 opened Nov 12, 2020 by konstantinmiller
1
Error when loading a model cloned without git-lfs is quite cryptic
#8497 opened Nov 12, 2020 by thomwolf
1
error occurs when trainning transformer-xl by ddp
#8494 opened Nov 12, 2020 by ismymajia
`log_history` does not contain metrics anymore
#8487 opened Nov 12, 2020 by PhilipMay
1
Gradient accumulation averages over gradients
#8486 opened Nov 12, 2020 by MarktHart
1
transformers.TFTrainer: Does not support batches with sequences of variable lengths?
#8483 opened Nov 12, 2020 by JulesGM
1
Error when upload models: "LFS: Client error"
#8480 opened Nov 12, 2020 by danyaljj
8
ProTip! Add no:assignee to see everything that’s not assigned.
You can’t perform that action at this time.