Commits · efeb6b1a0de79234e3fc19586212da2701fb05e1 · chenpangpang / transformers

"model_cards/vscode:/vscode.git/clone" did not exist on "9f1544b9e00f9b0cc01559a934e1fc6ae79af4cc"

07 Nov, 2018 1 commit
- cleaning up - speeding up a bit multi-gpu · dbc318a4
  thomwolf authored Nov 07, 2018
  
  dbc318a4
06 Nov, 2018 1 commit
- fixing weights initialization in the model and out of span clamping · 2a97fe22
  thomwolf authored Nov 06, 2018
  
  2a97fe22
05 Nov, 2018 3 commits
- ignore SQuAD targets outside of seq_length · c3527cfb
  thomwolf authored Nov 05, 2018
  
  c3527cfb
- fix multi-gpu squad loss · 2f4765d3
  thomwolf authored Nov 05, 2018
  
  2f4765d3
- fixing BertForQuestionAnswering loss computation · a725db4f
  thomwolf authored Nov 05, 2018
  
  a725db4f
04 Nov, 2018 3 commits
- clean up model · d0cb9fa2
  thomwolf authored Nov 04, 2018
  
  d0cb9fa2
- logging + update copyright · 834b485b
  thomwolf authored Nov 04, 2018
  
  834b485b
- add tqdm, clean up logging · 0b7a20c6
  thomwolf authored Nov 04, 2018
  
  0b7a20c6
03 Nov, 2018 6 commits
- update readme, file names, removing TF code, moving tests · f8276008
  thomwolf authored Nov 03, 2018
  
  f8276008
- fix typo · f18ae210
  Ubuntu authored Nov 03, 2018
  
  f18ae210
- special edition script · 04287a4d
  thomwolf authored Nov 03, 2018
  
  04287a4d
- `scatter_` and `scatter` · 2c55568c
  VictorSanh authored Nov 03, 2018
  
  2c55568c
- comment on gelu function · e6d106a0
  thomwolf authored Nov 03, 2018
  
  e6d106a0
- fixing model · 8aa22af0
  thomwolf authored Nov 03, 2018
  
  8aa22af0
02 Nov, 2018 10 commits
- Fix loss · 72ab1039
  VictorSanh authored Nov 02, 2018
```
Please review @thomwolf but i think this is equivqlent (and it mimics the loss computation of the original loss)
```
  72ab1039
- Fix scatter LopngTensor · 25d5ca48
  VictorSanh authored Nov 02, 2018
  
  25d5ca48
- device · e6a710f6
  VictorSanh authored Nov 02, 2018
  
  e6a710f6
- Fix loss computation for indexes bigger than max_seq_length. · 3ebf1a13
  VictorSanh authored Nov 02, 2018
  
  3ebf1a13
- model fixes + ipnb fixes · c84315ec
  thomwolf authored Nov 02, 2018
  
  c84315ec
- run_squad WIP · e61db0d1
  thomwolf authored Nov 02, 2018
  
  e61db0d1
- implemented BertForQuestionAnswering · c0065af6
  thomwolf authored Nov 02, 2018
  
  c0065af6
- various fixes · dee09a40
  thomwolf authored Nov 02, 2018
  
  dee09a40
- small tweaks · 2c731fd1
  thomwolf authored Nov 02, 2018
  
  2c731fd1
- model training loop working – still have to check that everything is exactly same · 9343a231
  thomwolf authored Nov 02, 2018
  
  9343a231
01 Nov, 2018 6 commits
- run_classifier WIP + added classifier head and initialization to the model · f690f0e1
  thomwolf authored Nov 02, 2018
  
  f690f0e1
- run_classifier WIP · 4a0b59e9
  thomwolf authored Nov 01, 2018
  
  4a0b59e9
- convertion script WIP · ab0e8932
  thomwolf authored Nov 01, 2018
  
  ab0e8932
- added conversion script · c5d532e5
  thomwolf authored Nov 01, 2018
  
  c5d532e5
- working on model · 71557b16
  thomwolf authored Nov 01, 2018
  
  71557b16
- model conversion WIP · 1b95daa0
  thomwolf authored Nov 01, 2018
  
  1b95daa0
31 Oct, 2018 1 commit
- adding pytorch model file · da017ac9
  thomwolf authored Oct 31, 2018
  
  da017ac9