|
|
fix typo in data/README
|
 Runqi Yang
|
|
6 years ago |
|
|
Enforce upper-bound on maximum generation length (#121)
|
 Myle Ott
|
|
6 years ago |
|
|
Merge pull request #116 from facebookresearch/oss-merge-internal
|
 Sergey Edunov
|
|
6 years ago |
|
|
Allow more flexible pre-processing and generation (#227)
|
Sergey Edunov
|
|
6 years ago |
|
|
Filter padding properly in LabelSmoothedCrossEntropyCriterion (#229)
|
Myle Ott
|
|
6 years ago |
|
|
Small fixes
|
Myle Ott
|
|
6 years ago |
|
|
Use ATen built-in conv_tbc method (#66)
|
 James Reed
|
|
6 years ago |
|
|
More updates for PyTorch (#114)
|
Myle Ott
|
|
6 years ago |
|
|
More fixes for recent PyTorch (incl. topk issue) (#113)
|
Myle Ott
|
|
6 years ago |
|
|
Merge pull request #107 from facebookresearch/oss-merge-internal
|
Sergey Edunov
|
|
6 years ago |
|
|
Making our code compatible with the latest pytorch (#223)
|
Sergey Edunov
|
|
6 years ago |
|
|
Refactor incremental generation to be more explicit and less magical (#222)
|
Myle Ott
|
|
6 years ago |
|
|
Fix LabelSmoothedCrossEntropy test
|
Myle Ott
|
|
6 years ago |
|
|
pytorch update: no need to rewrap variable in backward()
|
Myle Ott
|
|
6 years ago |
|
|
Add support to prefixes (#221)
|
 Dario Pavllo
|
|
6 years ago |
|
|
More unit test fixes
|
Myle Ott
|
|
6 years ago |
|
|
Fix tests and flake8
|
Myle Ott
|
|
6 years ago |
|
|
Add OOM counter back to logging output
|
Myle Ott
|
|
6 years ago |
|
|
fairseq-py goes distributed (#106)
|
Myle Ott
|
|
6 years ago |
|
|
Allow larger maxlen (fixes #100) (#101)
|
Myle Ott
|
|
6 years ago |
|
|
Adjust weight decay by the current learning rate to make it work correctly during annealing
|
 Sergey Edunov
|
|
6 years ago |
|
|
Merge pull request #91 from facebookresearch/prepare_wmt
|
Sergey Edunov
|
|
6 years ago |
|
|
spelling
|
Sergey Edunov
|
|
6 years ago |
|
|
Update README with new models
|
Sergey Edunov
|
|
6 years ago |
|
|
Merge pull request #95 from bastings/patch-1
|
Sergey Edunov
|
|
6 years ago |
|
|
Adding README and more parameters to En2De script
|
Sergey Edunov
|
|
6 years ago |
|
|
Ratio should be predlen/reflen not reflen/predlen
|
 Joost Bastings
|
|
6 years ago |
|
|
Merge branch 'master' of github.com:facebookresearch/fairseq-py into prepare_wmt
|
Sergey Edunov
|
|
6 years ago |
|
|
Switch to news-commentary-v12
|
Sergey Edunov
|
|
6 years ago |
|
|
Fixed Weight Decay Regularization in Adam
|
 Michael Auli
|
|
6 years ago |
Connect to our Discord channel
Models
Annotations