- 30 Aug, 2019 1 commit
-
-
thomwolf authored
-
- 28 Aug, 2019 1 commit
-
-
Shijie Wu authored
-
- 24 Aug, 2019 1 commit
-
-
Shijie Wu authored
-
- 23 Aug, 2019 1 commit
-
-
Shijie Wu authored
Tokenization behave the same as original XLM proprocessing for most languages except zh, ja and th; Change API to allow specifying language in `tokenize`
-
- 20 Aug, 2019 2 commits
-
-
Guillem Garc铆a Subies authored
-
Guillem Garc铆a Subies authored
-
- 12 Aug, 2019 1 commit
-
-
LysandreJik authored
-
- 09 Aug, 2019 1 commit
-
-
LysandreJik authored
-
- 16 Jul, 2019 1 commit
-
-
thomwolf authored
-
- 15 Jul, 2019 1 commit
-
-
thomwolf authored
-
- 10 Jul, 2019 3 commits
-
-
LysandreJik authored
Fixed file extensions for config/vocab/merges of XLM models.
-
LysandreJik authored
-
LysandreJik authored
Fixed all links. Removed TPU. Changed CLI to Converting TF models. Many minor formatting adjustments. Added "TODO Lysandre filled" where necessary.
-
- 09 Jul, 2019 2 commits
- 05 Jul, 2019 3 commits
- 03 Jul, 2019 2 commits
- 02 Jul, 2019 1 commit
-
-
thomwolf authored
-
- 17 Jun, 2019 1 commit
-
-
thomwolf authored
-
- 08 May, 2019 1 commit
-
-
thomwolf authored
-
- 16 Apr, 2019 2 commits
- 15 Apr, 2019 4 commits
- 06 Mar, 2019 1 commit
-
-
thomwolf authored
-
- 03 Mar, 2019 1 commit
-
-
Catalin Voss authored
For many applications requiring randomized data access, it's easier to cache the tokenized representations than the words. So why not turn this into a warning?
-
- 13 Feb, 2019 1 commit
-
-
thomwolf authored
-
- 11 Feb, 2019 1 commit
-
-
thomwolf authored
-
- 07 Feb, 2019 1 commit
-
-
thomwolf authored
-
- 05 Feb, 2019 1 commit
-
-
thomwolf authored
-
- 04 Feb, 2019 4 commits
- 28 Jan, 2019 1 commit
-
-
thomwolf authored
-