9 Commits

Author	SHA1	Message	Date
theblackcat102	bcebbbc49c	[merge] Fix conflict	2023-02-11 00:23:25 +00:00
jack.butler	24b07523aa	add test for tokenizer matching behaviour	2023-02-10 09:47:20 +00:00
jack.butler	090c5cbcc2	fix tokenizer matching and add tests	2023-02-09 18:47:38 +00:00
theblackcat102	1041564db7	[feature] mix generation from different tasks	2023-02-03 00:15:29 +00:00
theblackcat102	62a203fd8c	[feature] move data formatting into dataset, instead of collator	2023-01-21 03:31:35 +00:00
theblackcat102	aca3e9de89	[fix] wait it pass?	2023-01-20 07:26:26 +00:00
theblackcat102	74cb9aaa5a	[feature] added translation, rallio instruct tuning dataset, prosocial for safety, new summary dataset	2023-01-20 03:02:07 +00:00
theblackcat102	1546111094	[feature] added GSM8k and code refactoring	2023-01-14 06:24:47 +00:00
theblackcat102	3966024871	[fix] Fix summarizer bug and QA typo issue	2023-01-14 05:49:22 +00:00