The Wayback Machine - https://web.archive.org/web/20200526204112/https://github.com/pytorch/fairseq/issues
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

222 Open 1,305 Closed
222 Open 1,305 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
👍 👎 😄 🎉 😕 ❤️ 🚀 👀
How to use external langauge model in speech recognition task? needs triage question
#2185 opened May 26, 2020 by LeeYongHyeok
Validation happens after every epoch, validate_interval is ignored bug
#2182 opened May 26, 2020 by villmow
@myleott
1
Set learning late for transformer base with 50 batch size and update freq of 1 needs triage question
#2180 opened May 25, 2020 by ajesujoba
How to reproduce fine-tuning en-zh with mBART? needs triage question
#2179 opened May 25, 2020 by thpun
mBart cc25 extract features doesn't work bug needs triage
#2178 opened May 24, 2020 by shonenkov
Fix bad error message in FastBPE documentation
#2177 opened May 23, 2020 by AmirAktify
@myleott
Generating Alignments take longer time than prediction on a GPU bug needs triage
#2173 opened May 22, 2020 by gvskalyan
1
How to get an attention matrix when we evaluate the transformer model on translation task? needs triage question
#2171 opened May 22, 2020 by gtshs2
How to fine tune roberta for multi-label classification? needs triage question
#2169 opened May 21, 2020 by neelansh
1
Lazy GroupedIterator for less spiky dataloading enhancement help wanted needs triage
#2168 opened May 21, 2020 by Tetratrio
size mismatch when loading mbart pretrained model needs triage question
#2167 opened May 21, 2020 by beichao1314
OverflowError: cannot serialize a bytes object larger than 4 GiB question
#2166 opened May 21, 2020 by yuan-commits
6
Translation BLEU for WMT19 based of numbers of checkpoint files loaded
#2164 opened May 20, 2020 by Oxi84
[Quant-noise] How to properly load the quantized model? question
#2161 opened May 20, 2020 by bdropuljic
2
Mapping embedding matrix back to words question
#2158 opened May 20, 2020 by NadjaHergerTR
1
"Note that ASG loss currently doesn't do well with word-pieces" needs triage question
#2155 opened May 19, 2020 by SeanNaren
RuntimeError: index out of range: Tried to access index 300 out of table with 299 needs triage question
#2154 opened May 19, 2020 by AhmedTElthakeb
How to tune mbart pretrained model for an unsupervised MT? needs triage question
#2149 opened May 19, 2020 by masonreznov
Using custom modules for data throws `ModuleNotFouldError` bug
#2143 opened May 17, 2020 by Tetratrio
@myleott
1
Training with Fairseq 0.7.2 version is too slow and not converging well compare to previous Fairseq version Unable To Reproduce question
#2142 opened May 17, 2020 by jalajthanaki
3
stats[args.best_checkpoint_metric] -> KeyError: 'loss' documentation
#2141 opened May 16, 2020 by cyk1337
@myleott
4
Save last checkpoint before validation enhancement help wanted
#2140 opened May 16, 2020 by villmow
@myleott
Shared weights are duplicated in checkpoints bug
#2138 opened May 15, 2020 by fansiawang
@myleott
2
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
ProTip! Mix and match filters to narrow down what you’re looking for.
You can’t perform that action at this time.