Commits · dc13e276eec4ae8f316c82a190095380ad19e3c5 · chenpangpang / transformers

"git@developer.sourcefind.cn:sugon_wxj/megatron-lm.git" did not exist on "aff99e32b48582af674fd0ffbd3452252d4576a3"

01 Dec, 2018 1 commit
- Point typo fix · dc13e276
  Davide Fiocco authored Dec 01, 2018
  
  dc13e276
30 Nov, 2018 20 commits
- Merge pull request #72 from NirantK/patch-1 · 836b40be
  Thomas Wolf authored Nov 30, 2018
```
Fix internal hyperlink typo
```
  836b40be
- Merge pull request #73 from huggingface/third-release · 66d50ca6
  Thomas Wolf authored Nov 30, 2018
```
Third release
```
  66d50ca6
- update readme · f9f3bdd6
  thomwolf authored Nov 30, 2018
  
  f9f3bdd6
- tup => tpu · 52ff0590
  thomwolf authored Nov 30, 2018
  
  52ff0590
- update new token classification model · 511bce58
  thomwolf authored Nov 30, 2018
  
  511bce58
- bump up version · 258eb500
  thomwolf authored Nov 30, 2018
  
  258eb500
- improve docstrings and fix new token classification model · d787c6be
  thomwolf authored Nov 30, 2018
  
  d787c6be
- add new token classification model · ed302a73
  thomwolf authored Nov 30, 2018
  
  ed302a73
- clean up classification model output · 89d47230
  thomwolf authored Nov 30, 2018
  
  89d47230
- tests for all model classes with and without labels · 7f7c41b0
  thomwolf authored Nov 30, 2018
  
  7f7c41b0
- Fix internal hyperlink typo · be57c8ee
  Nirant authored Dec 01, 2018
  
  be57c8ee
- Merge pull request #70 from deepset-ai/fix_lm_loss · 8c7267f1
  Thomas Wolf authored Nov 30, 2018
```
fix typo in input for masked lm loss function
```
  8c7267f1
- fix typo in input for masked lm loss function · 7b3bb8c0
  Malte Pietsch authored Nov 30, 2018
  
  7b3bb8c0
- fix pickle dump in run_squad example · 257a3513
  thomwolf authored Nov 30, 2018
  
  257a3513
- fix run_squad · c588453a
  thomwolf authored Nov 30, 2018
  
  c588453a
- 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
- add do_lower_case in examples · 05414425
  thomwolf authored Nov 30, 2018
  
  05414425
28 Nov, 2018 3 commits
- Merge pull request #60 from davidefiocco/patch-1 · 3951c2c1
  Thomas Wolf authored Nov 28, 2018
```
Updated quick-start example with `BertForMaskedLM`
```
  3951c2c1
- Updated quick-start example with `BertForMaskedLM` · ec2c339b
  Davide Fiocco authored Nov 28, 2018
```
As `convert_ids_to_tokens` returns a list, the code in the README currently throws an `AssertionError`, so I propose I quick fix.
```
  ec2c339b
- Merge pull request #58 from lliimsft/master · 21f01964
  Thomas Wolf authored Nov 28, 2018
```
Bug fix in examples;correct t_total for distributed training;run pred…
```
  21f01964
27 Nov, 2018 1 commit
- Bug fix in examples;correct t_total for distributed training;run prediction for full dataset · 0aaedcc0
  Li Li authored Nov 27, 2018
  
  0aaedcc0
26 Nov, 2018 7 commits
- remove convert_to_unicode and printable_text from examples · 32167cdf
  thomwolf authored Nov 26, 2018
  
  32167cdf
- bump version in setup.py · ce37b8e4
  thomwolf authored Nov 26, 2018
  
  ce37b8e4
- update cache_dir in readme and examples · 05053d16
  thomwolf authored Nov 26, 2018
  
  05053d16
- added cache_dir option in from_pretrained · 63ae5d21
  thomwolf authored Nov 26, 2018
  
  63ae5d21
- fixing readme examples · 029bdc0d
  thomwolf authored Nov 26, 2018
  
  029bdc0d
- fixing typo in docstring · ebaacba3
  thomwolf authored Nov 26, 2018
  
  ebaacba3
- fixing target size in crossentropy losses · 870d7163
  thomwolf authored Nov 26, 2018
  
  870d7163
23 Nov, 2018 1 commit
- fixing unicode error · 982339d8
  thomwolf authored Nov 23, 2018
  
  982339d8
21 Nov, 2018 1 commit
- fix link in readme · 60e01ac4
  Thomas Wolf authored Nov 21, 2018
  
  60e01ac4
20 Nov, 2018 6 commits
- fixing weights decay in run_squad example · 6b2136a8
  thomwolf authored Nov 20, 2018
  
  6b2136a8
- Merge pull request #32 from xiaoda99/master · 061eeca8
  Thomas Wolf authored Nov 20, 2018
```
Fix ineffective no_decay bug when using BERTAdam
```
  061eeca8
- Merge pull request #42 from weiyumou/master · fd32ebed
  Thomas Wolf authored Nov 20, 2018
```
Fixed UnicodeDecodeError: 'ascii' codec can't decode byte 0xc2
```
  fd32ebed
- fixing CLI typo in readme · eed255a5
  thomwolf authored Nov 20, 2018
  
  eed255a5
- fixing param.grad is None in fp16 examples · 2f21497d
  thomwolf authored Nov 20, 2018
  
  2f21497d
- Fixed README typo · 9ff2b7d8
  weiyumou authored Nov 19, 2018
  
  9ff2b7d8