"git@developer.sourcefind.cn:sugon_wxj/megatron-lm.git" did not exist on "730266ca31974d557efe3dfbf0f2ec0650572aec"
- 08 Sep, 2019 1 commit
-
-
thomwolf authored
-
- 04 Sep, 2019 5 commits
- 02 Sep, 2019 2 commits
-
-
LysandreJik authored
-
thomwolf authored
-
- 31 Aug, 2019 19 commits
-
-
LysandreJik authored
-
LysandreJik authored
-
LysandreJik authored
-
LysandreJik authored
-
LysandreJik authored
-
LysandreJik authored
-
thomwolf authored
-
LysandreJik authored
-
LysandreJik authored
-
LysandreJik authored
-
LysandreJik authored
-
LysandreJik authored
Now raises a warning when a head to be deleted already has been deleted. An integration test verifying the total pipeline (-> from config -> save model -> load model -> additional head pruning) has been added.
-
LysandreJik authored
-
LysandreJik authored
-
Lysandre authored
-
LysandreJik authored
-
LysandreJik authored
-
Julien Chaumond authored
See #1089 cc @thomwolf @lysandrejik Also @dhpollack
-
Julien Chaumond authored
Instead we correctly store it on the config (regenerating the hosted config files) cc @lysandrejik
-
- 30 Aug, 2019 13 commits
-
-
thomwolf authored
-
thomwolf authored
-
thomwolf authored
-
thomwolf authored
-
LysandreJik authored
-
thomwolf authored
-
LysandreJik authored
-
LysandreJik authored
Added multiple AutoModel classes: AutoModelWithLMHead, AutoModelForQuestionAnswering and AutoModelForSequenceClassification
-
thomwolf authored
-
thomwolf authored
-
thomwolf authored
-
thomwolf authored
-
thomwolf authored
-