- 09 Jul, 2019 3 commits
- 05 Jul, 2019 2 commits
- 03 Jul, 2019 3 commits
-
-
thomwolf authored
-
thomwolf authored
-
LysandreJik authored
TorchScript flag in config; Tied weights when not running TorchScript; tuple concatenation clean-up.
-
- 02 Jul, 2019 4 commits
-
-
LysandreJik authored
-
thomwolf authored
-
thomwolf authored
-
thomwolf authored
-
- 26 Jun, 2019 2 commits
- 20 Jun, 2019 1 commit
-
-
thomwolf authored
-
- 19 Jun, 2019 2 commits
- 18 Jun, 2019 2 commits
- 17 Jun, 2019 4 commits
- 14 Jun, 2019 1 commit
-
-
thomwolf authored
-
- 01 Jun, 2019 2 commits
-
-
VictorSanh authored
cc @thomwolf
-
VictorSanh authored
-
- 08 May, 2019 3 commits
- 07 May, 2019 2 commits
- 30 Apr, 2019 3 commits
- 16 Apr, 2019 1 commit
-
-
Abhi Sharma authored
This fix is in reference to issue #382. GPT2 can now be trained in mixed precision, which I've confirmed with testing. I also tested unconditional generation on multiple seeds before and after changing 1e10 to 1e4 and there was no difference. Please let me know if there is anything else I can do to make this pull request better. Thanks for all your work!
-
- 15 Apr, 2019 3 commits
- 27 Mar, 2019 1 commit
-
-
Catalin Voss authored
-
- 24 Mar, 2019 1 commit
-
-
Catalin Voss authored
-