Commits · 6d1233fa2f0711cb715a3f1466a5efc19732c9f1 · OpenDAS / Fairseq

13 Jun, 2019 1 commit

Switch to gzip for large WMT'18 ensemble (#803) · 6d1233fa

Myle Ott authored Jun 12, 2019

Summary:
It's so much faster to extract (3 minutes instead of 20).
Pull Request resolved: https://github.com/pytorch/fairseq/pull/803

Differential Revision: D15795810

Pulled By: myleott

fbshipit-source-id: 3b2ae8bd7924a77ac8e795f5e1a7da0c4ae27374

6d1233fa

11 Jun, 2019 1 commit

Iterate on torch.hub interface · 5bdee18e

Myle Ott authored Jun 11, 2019

Summary: Pull Request resolved: https://github.com/pytorch/fairseq/pull/793

Differential Revision: D15758755

Pulled By: myleott

fbshipit-source-id: b93e4ac11bde36a0b59b4d6d1c84d31c3124d767

5bdee18e

25 Jan, 2019 1 commit

Add code for "Pay Less Attention with Lightweight and Dynamic Convolutions" (#473) · b41c74dc

Myle Ott authored Jan 25, 2019

Summary:
Changelog:
- `e330f56`: Add code for the "Pay Less Attention with Lightweight and Dynamic Convolutions" paper
- `5e3b98c`: Add scripts for computing tokenized BLEU with compound splitting and sacrebleu
- update READMEs
- misc fixes
Pull Request resolved: https://github.com/pytorch/fairseq/pull/473

Differential Revision: D13819717

Pulled By: myleott

fbshipit-source-id: f2dc12ea89a436b950cafec3593ed1b04af808e9

b41c74dc