285 Commits

Author	SHA1	Message	Date
thomwolf	e55d4c4ede	various updates to conversion, models and examples	2019-06-26 00:57:53 +02:00
thomwolf	603c513b35	update main conversion script and readme	2019-06-25 10:45:07 +02:00
thomwolf	7de1740490	add ability to restore fine-tuned TF mdoel	2019-06-25 10:27:58 +02:00
thomwolf	62d78aa37e	updating GLUE utils for compatibility with XLNet	2019-06-24 14:36:11 +02:00
thomwolf	24ed0b9346	updating run_xlnet_classifier	2019-06-24 12:00:09 +02:00
thomwolf	f6081f2255	add xlnetforsequence classif and run_classifier example for xlnet	2019-06-24 10:01:07 +02:00
thomwolf	c946bb51a6	fix xlnet tokenizer and python2	2019-06-22 22:28:49 +02:00
thomwolf	181075635d	updating model loading and adding special tokens ids	2019-06-21 23:23:37 +02:00
thomwolf	ebd2cb8d74	update from_pretrained to load XLNetModel as well	2019-06-21 21:08:44 +02:00
thomwolf	483cbc36a9	test deviation with tf model: max ~1e-3 should be ok	2019-06-21 16:38:01 +02:00
thomwolf	24d8068982	weights loading script ok	2019-06-21 12:33:44 +02:00
thomwolf	32da75486b	add tokenizer and tests	2019-06-21 11:09:51 +02:00
thomwolf	45709d7532	model running with simple inputs	2019-06-21 00:28:42 +02:00
thomwolf	c2ea5aef77	work in progress on xlnet	2019-06-20 13:52:21 +02:00
thomwolf	de713fa9b4	starting	2019-06-20 10:54:19 +02:00
thomwolf	7f00a36e27	pruning should keep on device	2019-06-19 22:23:12 +02:00
thomwolf	34d706a0e1	pruning in bertology	2019-06-19 15:25:49 +02:00
thomwolf	dc8e0019b7	updating examples	2019-06-19 13:23:20 +02:00
thomwolf	68ab9599ce	small fix and updates to readme	2019-06-19 09:38:38 +02:00
thomwolf	4d8c4337ae	test barrier in distrib training	2019-06-18 22:41:28 +02:00
thomwolf	868de8d1d7	updating weights loading	2019-06-18 10:58:20 +02:00
thomwolf	64e0adda81	better error message	2019-06-18 10:51:31 +02:00
thomwolf	382e2d1e50	spliting config and weight files for bert also	2019-06-18 10:37:16 +02:00
thomwolf	33d3db5c43	updating head masking, readme and docstrings	2019-06-17 15:51:28 +02:00
thomwolf	965f172de6	output all hidden layers states in GPT/GPT-2	2019-06-17 14:34:12 +02:00
thomwolf	f12007e421	add head masking and pruning to openai GPT	2019-06-17 14:19:40 +02:00
thomwolf	b860e47cf5	add head masking and pruning to gpt-2	2019-06-17 14:12:10 +02:00
thomwolf	7220d47a1c	adding head pruning and tests	2019-06-17 13:20:45 +02:00
thomwolf	8415a38b23	better error messages	2019-06-17 13:03:48 +02:00
thomwolf	96c4d3d988	add head masking tests	2019-06-17 12:17:26 +02:00
thomwolf	34858ae1d9	adding bert whole words, bertgerman and gpt-2 medium models, head masking	2019-06-17 11:02:39 +02:00
Thomas Wolf	80684f6f86	Merge pull request #690 from shashwath94/projadpsftmax_fix ... Transformer XL ProjectedAdaptiveLogSoftmax output fix	2019-06-15 23:14:10 +02:00
Thomas Wolf	9e363703d6	Merge pull request #688 from deepset-ai/german_bert ... Add German Bert model to code, update readme	2019-06-15 23:13:41 +02:00
vanche	8289646d4e	import class "GPT2MultipleChoiceHead"	2019-06-15 22:19:30 +09:00
Shashwath H A	5076a5daa7	Fix proj adp softmax output return when n_clusters=0	2019-06-14 22:03:21 -04:00
timoeller	16af9ff7b0	Add German Bert model to code, update readme	2019-06-14 17:42:46 +02:00
thomwolf	44e9ddd7fe	fix num_special_tokens in GPT 2 test	2019-06-14 17:17:43 +02:00
Thomas Wolf	ff276fc00c	Merge branch 'master' into finish_torchhub_interfaces	2019-06-14 16:59:07 +02:00
Thomas Wolf	35e6baab37	Merge branch 'master' into attention	2019-06-14 16:41:56 +02:00
thomwolf	5e1207b8ad	add attention to all bert models and add test	2019-06-14 16:28:25 +02:00
thomwolf	a3274ac40b	adding attention outputs in bert	2019-06-03 16:11:45 -05:00
VictorSanh	826496580b	Revert "add output_attentions for BertModel" ... This reverts commit de5e5682a1.	2019-06-03 17:10:25 -04:00
VictorSanh	de5e5682a1	add output_attentions for BertModel	2019-06-03 17:05:24 -04:00
VictorSanh	8f97f6c57f	fix typo ... cc @thomwolf	2019-06-01 17:29:07 -04:00
VictorSanh	c0c7ff5751	add transformer xl compatibility for torchhub	2019-06-01 16:08:24 -04:00
VictorSanh	a92b6dc3c1	add GPT2 torchhub compatibility	2019-06-01 15:27:43 -04:00
VictorSanh	0c5a4fe9c9	modify from_pretrained for OpenAIGPT	2019-05-31 00:27:18 -04:00
Victor SANH	96592b544b	default in __init__s for classification BERT models (#650)	2019-05-30 15:53:13 -04:00
thomwolf	275179a003	output attentions in GPT-2	2019-05-08 22:24:42 +02:00
thomwolf	366a3b0285	clean up in tokenization	2019-05-08 21:43:51 +02:00