Deyu Fu
|
3b0a14b761
|
add fallback path for apex used in modeling.py
|
2018-12-12 15:05:45 -08:00 |
|
Grégory Châtel
|
dcb50eaa4b
|
Swag example readme section update with gradient accumulation run.
|
2018-12-12 18:17:46 +01:00 |
|
Deyu Fu
|
c8ea286048
|
change to apex for better fp16 and multi-gpu support
|
2018-12-11 17:13:58 -08:00 |
|
hzhwcmhf
|
485adde742
|
add pathlib support for file_utils.py on python 3.5
|
2018-12-11 22:49:19 +08:00 |
|
hzhwcmhf
|
bc659f86ad
|
fix compatibility with python 3.5.2; convert path to str
|
2018-12-11 20:18:56 +08:00 |
|
thomwolf
|
1df6f26214
|
Merge branch 'fourth-release' of https://github.com/huggingface/pytorch-pretrained-BERT into fourth-release
|
2018-12-11 12:20:31 +01:00 |
|
thomwolf
|
770f805ae5
|
include version number + comment in setup.py
|
2018-12-11 12:20:22 +01:00 |
|
thomwolf
|
ed3b62cd3b
|
added version in __init__.py
|
2018-12-11 12:12:08 +01:00 |
|
Thomas Wolf
|
632f2d2df9
|
Merge branch 'master' into fourth-release
|
2018-12-11 06:00:53 -05:00 |
|
thomwolf
|
b13abfa9fe
|
add saving and loading model in examples
|
2018-12-11 11:58:07 +01:00 |
|
thomwolf
|
270fa2f20b
|
add pretrained loading from state_dict
|
2018-12-11 11:50:38 +01:00 |
|
Thomas Wolf
|
a3a3180c86
|
Bump up requirements to Python 3.6
|
2018-12-11 11:29:45 +01:00 |
|
Thomas Wolf
|
e7c0a8ddce
|
Merge pull request #107 from lliimsft/master
Fix optimizer to work with horovod
|
2018-12-11 05:18:00 -05:00 |
|
Thomas Wolf
|
e622790a93
|
Merge pull request #91 from rodgzilla/convert-examples-code-improvement
run_classifier.py improvements
|
2018-12-11 05:12:04 -05:00 |
|
Grégory Châtel
|
df34f22854
|
Removing the dependency to pandas and using the csv module to load data.
|
2018-12-10 17:45:23 +01:00 |
|
Grégory Châtel
|
0876b77f7f
|
Change to the README file to add SWAG results.
|
2018-12-10 15:34:19 +01:00 |
|
Li Li
|
81e1e2489f
|
Fix optimizer to work with horovod
|
2018-12-10 02:08:38 -08:00 |
|
thomwolf
|
174cdbccde
|
adding save checkpoint and loading in examples
|
2018-12-09 17:04:23 -05:00 |
|
thomwolf
|
1db916b5be
|
compatibility PT 1.0 and 0.4.1
|
2018-12-09 16:57:51 -05:00 |
|
thomwolf
|
68f77303b2
|
fixing Adam weights skip in TF convert script
|
2018-12-09 16:17:11 -05:00 |
|
Thomas Wolf
|
a2b6918a11
|
Merge pull request #101 from davidefiocco/patch-1
Adding --do_lower_case for all uncased BERTs examples
|
2018-12-09 15:29:31 -05:00 |
|
Thomas Wolf
|
5c858448d3
|
Merge pull request #94 from rodgzilla/fixing-squad-commentary
Fixing the commentary of the `SquadExample` class.
|
2018-12-09 15:27:30 -05:00 |
|
Davide Fiocco
|
c9f67e037c
|
Adding --do_lower_case for all uncased BERTs
I had missed those, it should make sense to use them
|
2018-12-07 20:40:56 +01:00 |
|
Grégory Châtel
|
150f3cd9fa
|
Few typos in README.md
|
2018-12-06 19:22:07 +01:00 |
|
Grégory Châtel
|
d429c15f25
|
Removing old code from copy-paste.
|
2018-12-06 19:19:21 +01:00 |
|
Grégory Châtel
|
4fa7892d64
|
Wrong line number link to modeling file.
|
2018-12-06 19:18:29 +01:00 |
|
Grégory Châtel
|
6a26e19ea3
|
Updating README.md with SWAG example informations.
|
2018-12-06 19:15:08 +01:00 |
|
Grégory Châtel
|
63c45056aa
|
Finishing the code for the Swag task.
|
2018-12-06 18:53:05 +01:00 |
|
Grégory Châtel
|
fc5a38ac92
|
Adding the BertForMultipleChoiceClass.
|
2018-12-06 18:42:23 +01:00 |
|
Grégory Châtel
|
c45d8ac554
|
Storing the feature of each choice as a dict for readability.
|
2018-12-06 16:01:28 +01:00 |
|
Grégory Châtel
|
0812aee2c3
|
Fixing problems in convert_examples_to_features.
|
2018-12-06 15:53:07 +01:00 |
|
Grégory Châtel
|
f2b873e995
|
convert_examples_to_features code and small improvements.
|
2018-12-06 15:40:47 +01:00 |
|
Grégory Châtel
|
83fdbd6043
|
Adding read_swag_examples to load the dataset.
|
2018-12-06 14:02:46 +01:00 |
|
Grégory Châtel
|
7183cded4e
|
SwagExample class.
|
2018-12-06 13:39:44 +01:00 |
|
Grégory Châtel
|
fa7daa247d
|
Fixing the commentary of the SquadExample class.
|
2018-12-06 13:14:33 +01:00 |
|
Grégory Châtel
|
a994bf4076
|
Fixing related to issue #83.
|
2018-12-05 18:16:30 +01:00 |
|
Grégory Châtel
|
c6d9d5394e
|
Simplifying code for easier understanding.
|
2018-12-05 17:53:09 +01:00 |
|
Grégory Châtel
|
793262e8ec
|
Removing trailing whitespaces.
|
2018-12-05 17:52:39 +01:00 |
|
Thomas Wolf
|
3ba5470eb8
|
Merge pull request #87 from rodgzilla/readme-file-links
Readme file links
|
2018-12-05 10:41:05 -05:00 |
|
Grégory Châtel
|
0a7c8bdcac
|
Fixing badly formatted links.
|
2018-12-04 13:43:56 +01:00 |
|
Grégory Châtel
|
3113e967db
|
Adding links to examples files.
|
2018-12-04 13:40:38 +01:00 |
|
Thomas Wolf
|
04826b0f2c
|
Merge pull request #77 from davidefiocco/patch-1
Correct assignement for logits in classifier example
|
2018-12-02 13:01:04 +01:00 |
|
Davide Fiocco
|
e60e8a6068
|
Correct assignement for logits in classifier example
I tried to address https://github.com/huggingface/pytorch-pretrained-BERT/issues/76
should be correct, but there's likely a more efficient way.
|
2018-12-02 12:38:26 +01:00 |
|
Thomas Wolf
|
063be09b71
|
Merge pull request #75 from davidefiocco/patch-2
Point typo fix
|
2018-12-01 01:15:43 +01:00 |
|
Thomas Wolf
|
4450f5ef6b
|
Merge pull request #74 from davidefiocco/patch-1
Update finetuning example in README adding --do_lower_case
|
2018-12-01 01:15:31 +01:00 |
|
Davide Fiocco
|
dc13e276ee
|
Point typo fix
|
2018-12-01 01:02:16 +01:00 |
|
Davide Fiocco
|
8a8aa59d8c
|
Update finetuning example adding --do_lower_case
Should be consistent with the fact that an uncased model is used
|
2018-12-01 01:00:05 +01:00 |
|
Thomas Wolf
|
836b40be82
|
Merge pull request #72 from NirantK/patch-1
Fix internal hyperlink typo
|
2018-11-30 23:33:53 +01:00 |
|
Thomas Wolf
|
66d50ca6ae
|
Merge pull request #73 from huggingface/third-release
Third release
|
2018-11-30 23:10:30 +01:00 |
|
thomwolf
|
f9f3bdd60b
|
update readme
|
2018-11-30 23:05:18 +01:00 |
|