19383 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Thomas Wolf	50e615f43d	Merge branch 'master' into improved_testing	2019-08-30 13:40:35 +02:00
thomwolf	f8aace6bcd	update tokenizers to use self.XX_token_id instead of converting self.XX_token	2019-08-30 13:39:52 +02:00
thomwolf	8faf2e086b	more doc on special tokens	2019-08-30 13:36:22 +02:00
Thomas Wolf	f7978490b2	Merge pull request #1148 from huggingface/circleci ... Documentation auto-deploy	2019-08-30 13:28:16 +02:00
thomwolf	ce5ef4b35d	python2 doesn't spark joy	2019-08-30 13:22:43 +02:00
thomwolf	5dd7b677ad	clean up all byte-level bpe tests	2019-08-30 12:43:08 +02:00
thomwolf	ca1a00a302	fix for python2	2019-08-30 12:29:31 +02:00
thomwolf	4e6a3172ce	update roberta docstring as well	2019-08-30 12:23:37 +02:00
thomwolf	fd10d79b55	update GPT2 docstring	2019-08-30 12:23:12 +02:00
thomwolf	abe734ca1f	fix GPT-2 and RoBERTa tests to be clean now	2019-08-30 12:20:18 +02:00
thomwolf	0f5a799456	fix GPT2DoubleHeadModel docstring	2019-08-30 11:49:23 +02:00
thomwolf	d51f72d5de	adding shortcut to the ids of all the special tokens	2019-08-30 11:41:11 +02:00
thomwolf	306af132d7	update readme to mention add_special_tokens more clearly in example	2019-08-30 11:30:51 +02:00
thomwolf	50e6daf83a	fix Roberta tokenizer __init__	2019-08-30 11:27:43 +02:00
thomwolf	0517e7a1cb	Fix GPT2 and RoBERTa tokenizer to beging with a space - update Roberta tokenizer	2019-08-30 11:23:49 +02:00
erenup	6e1ac34e2b	Merge remote-tracking branch 'huggingface/master'	2019-08-30 15:50:11 +08:00
jamin	2fb9a934b4	re-format	2019-08-30 14:05:28 +09:00
jamin	c8731b9583	update apex fp16 implementation	2019-08-30 13:54:00 +09:00
ziliwang	6060b2f89b	fix: hard coding for max number ... fp16 max number is 65504, the original 1e30 will cause Nan in fp16	2019-08-30 12:13:47 +08:00
epwalsh	07e21307b6	fix adding special tokens	2019-08-29 13:44:50 -07:00
LysandreJik	caf1d116a6	Closing bracket in DistilBERT's token count.	2019-08-29 15:30:10 -04:00
LysandreJik	e7fba4bef5	Documentation auto-deploy	2019-08-29 12:14:29 -04:00
Luis	fe8fb10b44	Small modification of comment in the run_glue.py example ... Add RoBERTa to the comment as it was not explicit that RoBERTa don't use token_type_ids.	2019-08-29 14:43:30 +02:00
erenup	2a2832ce73	Merge pull request #1 from erenup/run_multiple_choice ... roberta, xlnet for multiple choice	2019-08-29 16:27:44 +08:00
erenup	942d3f4b20	modifiy code of arc label insurance	2019-08-29 10:21:17 +08:00
LysandreJik	bf3dc778b8	Changed learning rate for run_squad test	2019-08-28 18:24:43 -04:00
thomwolf	0a74c88ac6	fix #1131	2019-08-28 22:41:42 +02:00
Thomas Wolf	5f297c7be3	Merge pull request #1087 from huggingface/fix-warnings ... Decode now calls private property instead of public method	2019-08-28 22:22:11 +02:00
Thomas Wolf	d9847678b3	Merge pull request #1136 from adai183/update_SQuAD_script ... swap order of optimizer.step() and scheduler.step()	2019-08-28 22:00:52 +02:00
Thomas Wolf	0f8ad89206	Merge pull request #1135 from stefan-it/master ... distilbert: fix number of hidden_size	2019-08-28 22:00:12 +02:00
LysandreJik	9ce42dc540	Pretrained models table fix	2019-08-28 13:56:28 -04:00
Andreas Daiminger	1d15a7f278	swap order of optimizer.step() and scheduler.step()	2019-08-28 19:18:27 +02:00
Stefan Schweter	ed2ab1c220	distilbert: fix number of hidden_size	2019-08-28 18:08:16 +02:00
Thomas Wolf	0ecfd17f49	Merge pull request #987 from huggingface/generative-finetuning ... Generative finetuning	2019-08-28 16:51:50 +02:00
Thomas Wolf	50792dbdcc	Merge pull request #1127 from huggingface/dilbert ... DilBERT	2019-08-28 16:43:09 +02:00
thomwolf	e7706f514b	update again	2019-08-28 16:37:22 +02:00
thomwolf	b5eb283aaa	update credits	2019-08-28 16:36:55 +02:00
LysandreJik	f753d4e32b	Removed typings for Python 2	2019-08-28 10:15:02 -04:00
LysandreJik	75bc2a03cc	Updated article link	2019-08-28 10:05:15 -04:00
LysandreJik	1dc43e56c9	Documentation additions	2019-08-28 09:37:27 -04:00
thomwolf	912a377e90	dilbert -> distilbert	2019-08-28 13:59:42 +02:00
thomwolf	c9bce1811c	fixing model to add torchscript, embedding resizing, head pruning and masking + tests	2019-08-28 13:22:45 +02:00
thomwolf	62df4ba59a	add dilbert tokenizer and tests	2019-08-28 12:22:56 +02:00
thomwolf	4ce5f36f78	update readmes	2019-08-28 12:14:31 +02:00
erenup	ec4b1c659f	logging truth error	2019-08-28 16:50:40 +08:00
erenup	df52abe373	add sep_toekn between question and choice	2019-08-28 16:36:21 +08:00
erenup	43c243254a	avoid invalid labels of truth	2019-08-28 16:03:17 +08:00
erenup	3c7e676f8b	add test related code: test the best dev acc model when model is training	2019-08-28 15:57:29 +08:00
VictorSanh	a5fe16687b	fix typo	2019-08-28 07:22:54 +00:00
VictorSanh	497f73c964	add DilBERT to master REAME	2019-08-28 07:16:30 +00:00