Commits · e1eab59aac9fdf5ebc062b1afe1d218d11d3a3d2 · chenpangpang / transformers

"...lm-evaluation-harness.git" did not exist on "8d7d21321bfc2f07278ab8d227c87a9040a95ee3"

13 Dec, 2018 2 commits
- clean up apex integration · 52c53f39
  thomwolf authored Dec 13, 2018
  
  52c53f39
- add pretrained loading from state_dict · 93f335ef
  thomwolf authored Dec 11, 2018
  
  93f335ef
12 Dec, 2018 2 commits
- add fallback path for apex used in modeling.py · 3b0a14b7
  Deyu Fu authored Dec 12, 2018
  
  3b0a14b7
- change to apex for better fp16 and multi-gpu support · c8ea2860
  Deyu Fu authored Dec 05, 2018
  
  c8ea2860
11 Dec, 2018 1 commit
- add pretrained loading from state_dict · 270fa2f2
  thomwolf authored Dec 11, 2018
  
  270fa2f2
06 Dec, 2018 1 commit
- Adding the BertForMultipleChoiceClass. · fc5a38ac
  Grégory Châtel authored Dec 06, 2018
  
  fc5a38ac
30 Nov, 2018 7 commits
- update new token classification model · 511bce58
  thomwolf authored Nov 30, 2018
  
  511bce58
- improve docstrings and fix new token classification model · d787c6be
  thomwolf authored Nov 30, 2018
  
  d787c6be
- fix typo in input for masked lm loss function · 7b3bb8c0
  Malte Pietsch authored Nov 30, 2018
  
  7b3bb8c0
- fixed loading pre-trained tokenizer from directory · d6f06c03
  thomwolf authored Nov 30, 2018
  
  d6f06c03
- fixed doc_strings · 532a81d3
  thomwolf authored Nov 30, 2018
  
  532a81d3
- added BertForTokenClassification model · 296f0061
  thomwolf authored Nov 30, 2018
  
  296f0061
- Added new bert models · 298107fe
  thomwolf authored Nov 30, 2018
  
  298107fe
26 Nov, 2018 3 commits
- added cache_dir option in from_pretrained · 63ae5d21
  thomwolf authored Nov 26, 2018
  
  63ae5d21
- fixing typo in docstring · ebaacba3
  thomwolf authored Nov 26, 2018
  
  ebaacba3
- fixing target size in crossentropy losses · 870d7163
  thomwolf authored Nov 26, 2018
  
  870d7163
15 Nov, 2018 1 commit
- preparing for first release · 1de35b62
  thomwolf authored Nov 15, 2018
  
  1de35b62