Skip to content

/ fairseq

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

214 Open 1,282 Closed
214 Open 1,282 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
👍 👎 😄 🎉 😕 ❤️ 🚀 👀
Get score of sentence using transformer model needs triage question
#2145 opened May 18, 2020 by AlexandderGorodetski
Using custom modules for data throws `ModuleNotFouldError` bug needs triage
#2143 opened May 17, 2020 by Tetratrio
1
Training with Fairseq 0.7.2 version is too slow and not converging well compare to previous Fairseq version needs triage question
#2142 opened May 17, 2020 by jalajthanaki
stats[args.best_checkpoint_metric] -> KeyError: 'loss' question
#2141 opened May 16, 2020 by cyk1337
3
Save last checkpoint before validation enhancement help wanted
#2140 opened May 16, 2020 by villmow
@myleott
same model size whether share_all_embedding or not bug
#2138 opened May 15, 2020 by fansiawang
@myleott
How to get the probabilities of the predictions for WSC needs triage question
#2136 opened May 14, 2020 by srininyu
wmt19 Text generator Length question
#2134 opened May 14, 2020 by AdaUchendu
1
[Quant-noise] Why reset quantization parameters frequently? question
#2132 opened May 14, 2020 by ChunhuanLin
1
[Quant-noise] Why p of ActivationQuantizer is set to 0 question
#2131 opened May 14, 2020 by ChunhuanLin
1
The train not save checkpoint Unable To Reproduce question
#2130 opened May 14, 2020 by zplovekq
3
Fine-tune BART for translation task on my own dataset question
#2125 opened May 13, 2020 by rathorevipul28
1
Runtime error Missing key(s) in state_dict: "decoder.output_projection.weight". When using 'eval_lm' question
#2124 opened May 12, 2020 by Sohyo
@myleott
2
Inference => RuntimeError: index out of range: Tried to access index 300 out of table with 299 question
#2123 opened May 12, 2020 by AhmedTElthakeb
2
Inconsistency of hyperparameters for Monotonic Multihead Attention between your README and the paper documentation needs triage
#2122 opened May 12, 2020 by shirley-wu
issues with pretrain mBART models needs triage question
#2120 opened May 11, 2020 by fansiawang
issues about finetune on mBART models needs triage question
#2119 opened May 11, 2020 by fansiawang
2
Change the first token in seq2seq architechture needs triage question
#2118 opened May 11, 2020 by redionxhepa
Adding more dataset source for mBART enhancement help wanted needs triage
#2117 opened May 11, 2020 by guoyinwang
how to use roberta to do speech_recognition task needs triage question
#2116 opened May 11, 2020 by luweishuang
Easier pipeline to apply back-translation on text as an augmentation method enhancement help wanted needs triage
#2115 opened May 11, 2020 by shamanez
1
Is `eval-bleu` supported when training Levenshtein transformer? needs triage question
#2114 opened May 9, 2020 by TingxunShi
About the function of lprobs[lprobs != lprobs] = torch.tensor(-math.inf).to(lprobs) in sequence_generator.py line 270 needs triage question
#2111 opened May 9, 2020 by yadongxi
How to preprocess for multilingual denoising (mBART) or MLM (XLM) needs triage question
#2110 opened May 8, 2020 by cbaziotis
Hyperparameter Optimization Task Best Practices needs triage question
#2109 opened May 8, 2020 by AlanHassen
ProTip! Type g i on any issue or pull request to go back to the issue listing page.
You can’t perform that action at this time.