17 Commits

Author	SHA1	Message	Date
Aleksandras Kostarevas	4f15ff4a73	Add experimental swipe typing	2023-11-28 17:01:58 +00:00
Aleksandras Kostarevas	14fcb55565	Save LoRA-merged model after training	2023-11-14 20:40:00 +02:00
Aleksandras Kostarevas	b53a46b18d	Move training to CoroutineWorker	2023-11-14 17:23:08 +02:00
Aleksandras Kostarevas	38b06d7909	History logging and training based on log	2023-11-14 11:43:36 +02:00
Aleksandras Kostarevas	33be6fb3ed	Refactor LanguageModel invocation code	2023-11-13 16:44:52 +02:00
Aleksandras Kostarevas	ee8a81f12c	Initial fine-tuning	2023-11-07 16:48:48 +02:00
Aleksandras Kostarevas	8bb38c7ae3	Show visual feedback when will autocorrect	2023-11-02 17:56:56 +02:00
Aleksandras Kostarevas	af9cab5f2a	Don't return suggestions for non-English locales	2023-10-17 19:24:51 +03:00
Aleksandras Kostarevas	21bd35237d	Show indicator for transformer suggestions, lazily load model	2023-10-17 19:06:29 +03:00
Aleksandras Kostarevas	7c4531e32d	Fix crashes related to too large context	2023-10-16 18:24:00 +03:00
Aleksandras Kostarevas	1d29501673	Add option to toggle transformer LM	2023-10-16 17:35:01 +03:00
Aleksandras Kostarevas	c73fe16ddc	Add q8 model	2023-10-16 17:31:43 +03:00
Aleksandras Kostarevas	ec7cae6bbf	Disable globe key by default	2023-10-13 21:40:06 +03:00
Aleksandras Kostarevas	92480fd460	Adjust space probability and mustNotAutocorrect	2023-10-13 18:44:38 +03:00
Aleksandras Kostarevas	334619086b	Trim context and fix case for misautocorections	2023-10-13 18:32:57 +03:00
Aleksandras Kostarevas	b8539ce88a	Initial batched inference using llama_batch	2023-10-10 22:34:04 +03:00
Aleksandras Kostarevas	16fdb3629d	Add LanguageModel class	2023-09-28 19:42:29 +03:00