VictorSanh
|
936eb4c3ad
|
FIX small bugs in `run_classifier_pytorch.py`
|
2018-11-02 01:11:25 -04:00 |
VictorSanh
|
cc228089ef
|
Small fix to ensure Python3 compativility.
|
2018-11-02 00:02:36 -04:00 |
thomwolf
|
ebfffa0ab2
|
updated extract_features
|
2018-11-02 04:32:18 +01:00 |
thomwolf
|
9af479b3b9
|
conversion run_squad ok
|
2018-11-02 04:12:20 +01:00 |
thomwolf
|
8e81e5e6ff
|
working on squad
|
2018-11-02 04:07:52 +01:00 |
thomwolf
|
e61db0d1c0
|
run_squad WIP
|
2018-11-02 03:56:14 +01:00 |
thomwolf
|
c0065af6cb
|
implemented BertForQuestionAnswering
|
2018-11-02 03:04:34 +01:00 |
thomwolf
|
5383fca458
|
update name
|
2018-11-02 01:56:25 +01:00 |
thomwolf
|
dee09a40b2
|
various fixes
|
2018-11-02 01:52:54 +01:00 |
thomwolf
|
2c731fd129
|
small tweaks
|
2018-11-02 01:38:22 +01:00 |
thomwolf
|
9343a2311b
|
model training loop working – still have to check that everything is exactly same
|
2018-11-02 01:31:31 +01:00 |
thomwolf
|
f690f0e167
|
run_classifier WIP + added classifier head and initialization to the model
|
2018-11-02 00:27:50 +01:00 |
thomwolf
|
4a0b59e980
|
run_classifier WIP
|
2018-11-01 21:05:04 +01:00 |
VictorSanh
|
7af7f8173b
|
Fix oubli
|
2018-11-01 15:44:52 -04:00 |
thomwolf
|
e1bb7904d8
|
optimization_pytorch from OpenAI with adapted HP - check if there is weights decay on bias
|
2018-11-01 20:11:14 +01:00 |
VictorSanh
|
d3a8df6b9f
|
typos in `input_fn_builder`
|
2018-11-01 14:17:55 -04:00 |
VictorSanh
|
836faed985
|
wip
|
2018-11-01 14:17:12 -04:00 |
thomwolf
|
960ef4df3b
|
probably ok weights convertion script
|
2018-11-01 19:12:31 +01:00 |
thomwolf
|
ab0e8932a8
|
convertion script WIP
|
2018-11-01 18:00:20 +01:00 |
Tim Rault
|
5581edb4f6
|
Merge remote-tracking branch 'origin/master'
|
2018-11-01 17:55:40 +01:00 |
Tim Rault
|
cdd39d216e
|
Remove TensorFlow dependence in `tokenization_test_pytorch.py`
|
2018-11-01 17:55:30 +01:00 |
thomwolf
|
c5d532e5f6
|
added conversion script
|
2018-11-01 17:40:05 +01:00 |
VictorSanh
|
90d360a7a9
|
WIP
|
2018-11-01 12:09:23 -04:00 |
Tim Rault
|
f8e7c95db3
|
Remove TensorFlow dependence in `tokenization_pytorch.py`
|
2018-11-01 15:16:00 +01:00 |
thomwolf
|
71557b165e
|
working on model
|
2018-11-01 14:48:15 +01:00 |
Tim Rault
|
8627a675cd
|
Convert flags to argparse in 'create_pretraining_data_pytorch.py'
|
2018-11-01 12:49:45 +01:00 |
Tim Rault
|
2f49360de9
|
Convert flags to argparse in 'extract_features_pytorch.py'
|
2018-11-01 11:59:44 +01:00 |
Tim Rault
|
04a360bb10
|
Convert flags to argparse in 'run_pretraining_pytorch.py'
|
2018-11-01 11:40:26 +01:00 |
Tim Rault
|
371945cf07
|
Convert flags to argparse in 'run_squad_pytorch.py'
|
2018-11-01 11:17:49 +01:00 |
Tim Rault
|
8163baab64
|
Convert indentation from 2 spaces to 4 spaces
|
2018-11-01 09:39:04 +01:00 |
VictorSanh
|
555b7d66c9
|
`input_fn_builder` WIP
|
2018-11-01 02:10:46 -04:00 |
VictorSanh
|
f8e347b557
|
Convert all DataProcessors, _truncate_seq_pair and convert_examples_to_features
|
2018-11-01 01:33:01 -04:00 |
VictorSanh
|
b1dade34db
|
Convert flags to argparse in `run_classifier_pytorch.py`
|
2018-11-01 01:05:11 -04:00 |
thomwolf
|
1b95daa0c1
|
model conversion WIP
|
2018-11-01 02:22:50 +01:00 |
thomwolf
|
da017ac910
|
adding pytorch model file
|
2018-10-31 19:44:49 +01:00 |
thomwolf
|
13ee61e4de
|
switch to full google code
|
2018-10-31 18:46:03 +01:00 |
thomwolf
|
12e013dbac
|
added wordpiece - updated readme
|
2018-10-30 23:09:09 +01:00 |
thomwolf
|
ccce66be27
|
getting ready
|
2018-10-30 20:18:49 +01:00 |
Thomas Wolf
|
43badf217d
|
Initial commit
|
2018-10-29 14:56:02 +01:00 |