228 Commits

Author	SHA1	Message	Date
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	270fa2f20b	add pretrained loading from state_dict	2018-12-11 11:50:38 +01:00
Li Li	81e1e2489f	Fix optimizer to work with horovod	2018-12-10 02:08:38 -08:00
thomwolf	68f77303b2	fixing Adam weights skip in TF convert script	2018-12-09 16:17:11 -05:00
Grégory Châtel	fc5a38ac92	Adding the BertForMultipleChoiceClass.	2018-12-06 18:42:23 +01:00
thomwolf	511bce58bd	update new token classification model	2018-11-30 22:56:02 +01:00
thomwolf	d787c6be8c	improve docstrings and fix new token classification model	2018-11-30 22:55:26 +01:00
thomwolf	ed302a73f4	add new token classification model	2018-11-30 22:55:03 +01:00
thomwolf	d6f06c03f4	fixed loading pre-trained tokenizer from directory	2018-11-30 14:09:06 +01:00
thomwolf	532a81d3d6	fixed doc_strings	2018-11-30 13:57:01 +01:00
thomwolf	296f006132	added BertForTokenClassification model	2018-11-30 13:56:53 +01:00
thomwolf	298107fed7	Added new bert models	2018-11-30 13:56:02 +01:00
thomwolf	32167cdf4b	remove convert_to_unicode and printable_text from examples	2018-11-26 23:33:22 +01:00
thomwolf	05053d163c	update cache_dir in readme and examples	2018-11-26 10:45:13 +01:00
thomwolf	63ae5d2134	added cache_dir option in from_pretrained	2018-11-26 10:21:56 +01:00
thomwolf	ebaacba38b	fixing typo in docstring	2018-11-26 09:55:15 +01:00
thomwolf	870d71636e	fixing target size in crossentropy losses	2018-11-26 09:51:34 +01:00
thomwolf	982339d829	fixing unicode error	2018-11-23 12:22:12 +01:00
weiyumou	37b6c9b21b	Fixed UnicodeDecodeError: 'ascii' codec can't decode byte 0xc2 in position 3793: ordinal not in range(128)	2018-11-19 23:01:28 -05:00
thomwolf	757750d6f6	fix tests	2018-11-17 11:58:14 +01:00
thomwolf	886cb49792	updating readme and notebooks	2018-11-16 14:31:15 +01:00
thomwolf	1de35b624b	preparing for first release	2018-11-15 20:56:10 +01:00