Commits · 6e4b7e22eeb79f7e1c39d862f10ec3e61e51c979 · OpenDAS / Fairseq

08 Nov, 2017 1 commit

Myle Ott authored Oct 25, 2017

* Move some functionality out of FConvModel into FairseqModel base class
* Move incremental decoding functionality into FairseqIncrementalDecoder module
* Refactor positional embeddings to be more specific to FConvModel

6e4b7e22

19 Oct, 2017 5 commits
- Fix handling of continuation tokens that precede <unk> in generate.py · ff2e8cf2
  Myle Ott authored Oct 17, 2017
  
  ff2e8cf2
- Simplify deps of build_model to only depend on dict (instead of dataset) · 84b82dc6
  Myle Ott authored Oct 17, 2017
  
  84b82dc6
- Fix flake8 warnings · cb0d7b2a
  Louis Martin authored Sep 25, 2017
  
  cb0d7b2a
- Support configurable BPE symbol · 7333d04d
  Myle Ott authored Sep 25, 2017
  
  7333d04d
- Move helper functions from generate.py to fairseq/dictionary.py · 59d599a2
  Myle Ott authored Sep 25, 2017
  
  59d599a2
11 Oct, 2017 3 commits
- Ignore invalid sentences in test and valid · 3f9b9838
  Sergey Edunov authored Oct 11, 2017
  
  3f9b9838
- Don't generate during training, add --quiet to generate.py · 8f058ea0
  Sergey Edunov authored Oct 11, 2017
  
  8f058ea0
- Update progress_bar to be more robust to changes in tqdm (#21) · 7aba6084
  Myle Ott authored Oct 11, 2017
  
  7aba6084
26 Sep, 2017 1 commit
- Fix generation when vocabulary is small relative to beam size (fixes #7) · 03c4a716
  Myle Ott authored Sep 26, 2017
  
  03c4a716
18 Sep, 2017 1 commit
- More fixes · c6de2190
  Sergey Edunov authored Sep 18, 2017
  
  c6de2190
15 Sep, 2017 1 commit
- Initial commit · e734b0fa
  Sergey Edunov authored Sep 14, 2017
  
  e734b0fa