289 Commits

Author	SHA1	Message	Date
Jack Morris	462620e074	trimming the fat; removing excess stuff; changing names	2020-06-18 11:12:36 -04:00
Jack Morris	90e6872eb4	ugly merge with recent master	2020-06-17 21:45:50 -04:00
Jack Morris	d6e90065c2	format pre-merge	2020-06-17 19:47:33 -04:00
Jack Morris	4d74aa5316	adding models; refactoring to use nlp datasets where possible	2020-06-17 19:39:56 -04:00
Jack Morris	2bbd06b0c2	merge in master & delete flaky test	2020-06-17 18:01:51 -04:00
Jack Morris	40b5640381	method for word insertion & additional tests	2020-06-17 17:43:42 -04:00
Jack Morris	dddf722aa3	support multiple workers on travis	2020-06-17 14:18:53 -04:00
Jin Yong Yoo	466ef97ade	make requested changes	2020-06-17 10:07:05 -04:00
Jin Yong Yoo	83b7fae8b2	resolve merge conflicts	2020-06-17 00:33:30 -04:00
Jack Morris	f0ad52e219	attacked_text tests	2020-06-17 00:33:14 -04:00
Jack Morris	a8418f8f75	update tokenizers	2020-06-16 23:52:03 -04:00
Jack Morris	d25bf44f52	update attackedtext references, need to update tokenization	2020-06-16 21:56:33 -04:00
Jack Morris	9bf213f7fd	TT->AttackedText, remove ids, give TT keys, batch tokenize	2020-06-16 19:46:20 -04:00
Jin Yong Yoo	b53206634b	modify shuffle, fix worklist	2020-06-16 13:30:55 -04:00
Jin Yong Yoo	686ae84909	resolve merge conflicts	2020-06-16 07:48:04 -04:00
Jack Morris	07e927e3e4	add isort and fix import loops, preparing to shorten tests	2020-06-15 20:40:44 -04:00
Jack Morris	ca535eb08e	adding SST cnn	2020-06-15 20:10:45 -04:00
Jack Morris	e93f456d07	reformatting	2020-06-15 19:41:44 -04:00
Jack Morris	1d8a172c05	code formatting; tokenizers->models/tokenizers	2020-06-15 18:36:04 -04:00
Jack Morris	fcb82dac5e	makefile and setup; need to fix imports	2020-06-15 17:07:12 -04:00
Jack Morris	c4329985a0	working on SST models and parallel memory issue	2020-06-15 13:55:07 -04:00
Jack Morris	8acf7aa728	PR updates [Tests pass]	2020-06-11 17:49:34 -04:00
Jack Morris	f0ff005fbb	fix merge with parse_attack/goal_function issue; tests pass	2020-06-11 13:00:27 -04:00
Jack Morris	3da7acf0df	merge [Tests pass]	2020-06-10 23:52:59 -04:00
Jack Morris	6a44f04f95	update docs & things; TP	2020-06-10 16:21:23 -04:00
Jack Morris	889954aaa9	test huggingface models; test attack from file; remove old files	2020-06-10 15:34:52 -04:00
Jack Morris	8b924362a5	standardize tokenization	2020-06-10 10:16:11 -04:00
Jack Morris	824cd9be8e	figured out huggingface tokenizers for benchmarking, now integrating into attack	2020-06-09 17:30:18 -04:00
Jack Morris	719514645c	good inference; problems with xlnet & roberta mnli	2020-06-09 16:37:10 -04:00
Jack Morris	753d429629	diagnosing tokenization discrepancies	2020-06-09 16:08:32 -04:00
Jack Morris	b1c262fada	merge & add boolean to transformation	2020-06-08 15:36:40 -04:00
Jack Morris	00170fe52c	fix master [duplicate line in args_helper]	2020-06-08 14:54:48 -04:00
Jack Morris	d66acde7ea	progress on all GLUE tasks	2020-06-08 14:46:23 -04:00
Jack Morris	f4d7ba0f1a	add --attack-from-file, unify tokenizers, add models from huggingface model hub [still need to verify acc]	2020-06-07 15:12:02 -04:00
Jin Yong Yoo	798a26efb9	add worklist for dealing with async logging	2020-06-07 11:59:14 -04:00
Jack Morris	3c68d02fb0	remove input reduction, change original_word_idx map to nparray, ignore first/last char for textbugger	2020-06-06 15:16:34 -04:00
Jack Morris	74b7dbb70a	default autotokenizer; add huggingface pre-loaded pre-trained stuff	2020-06-06 13:15:17 -04:00
Jack Morris	62d3a1070c	README; get_logger()->logger	2020-06-05 20:12:14 -04:00
Jack Morris	721a88978a	pretrained & file models/datasets; tests; get_logger() -> logger	2020-06-05 19:06:22 -04:00
uvafan	252b9d2064	fix typo	2020-06-05 18:24:46 -04:00
uvafan	298518afca	discussed fixes	2020-06-05 18:22:48 -04:00
Jack Morris	5222d4c604	successfully loading datasets from file	2020-06-05 18:01:53 -04:00
Jack Morris	b6dd920c08	support custom models; waiting on datasets integration	2020-06-05 17:35:52 -04:00
uvafan	ee95b82895	add query budget	2020-06-05 15:40:20 -04:00
Jack Morris	ab965e292b	account for idx shifts	2020-06-04 16:53:27 -04:00
Jack Morris	cab61ec436	typo	2020-06-04 16:11:59 -04:00
Jack Morris	e02b8e3e68	type validation for TT	2020-06-04 12:53:53 -04:00
Jack Morris	0261c4742e	fix tokenizers, tests pass	2020-06-03 20:41:29 -04:00
Jack Morris	7ca1473a8e	update tests and tokenizers	2020-06-03 19:56:29 -04:00
Jack Morris	f2fe8e1ad7	new -> newly	2020-06-03 18:24:45 -04:00