- 25 Jul, 2018 6 commits
-
-
Alexei Baevski authored
-
Stephen Roller authored
-
alexeib authored
-
alexeib authored
-
Alexei Baevski authored
-
higgsfield authored
-
- 20 Jul, 2018 1 commit
-
-
Angela Fan authored
-
- 19 Jul, 2018 1 commit
-
-
Sergey Edunov authored
-
- 11 Jul, 2018 1 commit
-
-
Mehdi Drissi authored
-
- 10 Jul, 2018 1 commit
-
-
Alexei Baevski authored
-
- 08 Jul, 2018 2 commits
-
-
Angela Fan authored
-
Angela Fan authored
add model override argument from load_ensemble_for_inference at generation time, updating readme for stories
-
- 02 Jul, 2018 2 commits
-
-
ngimel authored
-
Angela Fan authored
-
- 28 Jun, 2018 1 commit
-
-
Myle Ott authored
-
- 26 Jun, 2018 1 commit
-
-
Myle Ott authored
-
- 25 Jun, 2018 2 commits
- 24 Jun, 2018 3 commits
- 21 Jun, 2018 18 commits
-
-
Alexei Baevski authored
default samples_per_token in eval_lm
-
-
Myle Ott authored
-
Myle Ott authored
-
Myle Ott authored
-
alexeib authored
-
Alexei Baevski authored
-
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.
-
Mehdi Drissi authored
Two tiny changes to train/eval_lm. For train fix an off by one, while for eval_lm make it work when the task is translation'
-
Myle Ott authored
-
Myle Ott authored
-
- 20 Jun, 2018 1 commit
-
-
Angela Fan authored
-