- 21 Jun, 2018 10 commits
-
-
Myle Ott authored
-
Stephen Roller authored
Also show a nicer error message.
-
alexeib authored
-
alexeib authored
-
Stephen Roller authored
-
Myle Ott authored
-
Myle Ott authored
-
Louis MARTIN authored
When downloading files in examples directory (e.g. when running `prepare-iwslt14.sh`), git sees them as untracked files but they should not be committed. Add a .gitignore script that ignore everything in the examples subdirectories except for .sh and .md files.
-
Myle Ott authored
-
Myle Ott authored
-
- 20 Jun, 2018 4 commits
-
-
Angela Fan authored
-
Angela Fan authored
-
Angela Fan authored
-
ngimel authored
-
- 16 Jun, 2018 1 commit
-
-
Myle Ott authored
Fix preprocessed test set download links
-
- 15 Jun, 2018 25 commits
-
-
Myle Ott authored
Changelog: - 97b58b46: add Transformer model from Vaswani et al. (2017) - b2374e52: faster Transformer inference with improved caching - 2d27ae08: simulate large mini-batch training with delayed updates (`--update-freq`) - 7ee1d284: add FP16 training support (`--fp16`) - 2a84f46b: faster inference by removing completed sentences from the batch - 663fd806: batched interactive generation - 4c2ef2de: add language modeling / gated convolutional model from Dauphin et al. (2017) - b59815bc: add Hierarchical Neural Story Generation model from Fan et al. (2018) - ff68a9ef: add FairseqTask to modularize task definitions (e.g., translation, language modeling)
-
Myle Ott authored
Add transformer models and replace list with table
-
Alexei Baevski authored
-
alexeib authored
-
Myle Ott authored
-
Myle Ott authored
-
Myle Ott authored
-
Myle Ott authored
-
Myle Ott authored
-
Myle Ott authored
A Task defines the data format, stores shared state (e.g., dictionaries) and provides helpers for building the model/criterion and calculating the loss. Changes: - Add TranslationTask and LanguageModelingTask. New tasks can be registered with @register_task decorator. - Add EpochBatchIterator to encapsulate batching and saving/restoring dataloader position - Remove LEFT_PAD_* constants and make them configurable per task
-
Sergey Edunov authored
torch.arange default return type is changed in the latest pytorch version https://github.com/pytorch/pytorch/pull/7016
-
Myle Ott authored
Co-authored-by:pmichel31415 <pmichel@fb.com>
-
alexeib authored
-
Alexei Baevski authored
-
Myle Ott authored
-
Myle Ott authored
-
Myle Ott authored
-
Myle Ott authored
-
Alexei Baevski authored
-
Myle Ott authored
-
Myle Ott authored
-
Myle Ott authored
-
Myle Ott authored
-
Myle Ott authored
-
alexeib authored
-