144 Commits

All Branches

Search

Author	SHA1	Message	Date
Falko Victor Habel	674e5d5409	Merge pull request 'feat/tf_support' (#37) from feat/tf_support into develop ... Reviewed-on: #37	2025-04-16 20:59:47 +00:00
Falko Victor Habel	716f6e2470	increased version number	2025-04-13 22:20:42 +02:00
Falko Victor Habel	1190f3c05f	updated config to match new version	2025-04-13 22:19:59 +02:00
Falko Victor Habel	023ca07cf7	tests to pass new params	2025-04-13 22:19:38 +02:00
Falko Victor Habel	9ec01e2dd0	tests with new config	2025-04-13 22:19:15 +02:00
Falko Victor Habel	3e78a595c9	removed base aiia class and replaced it with transformer support	2025-04-13 22:18:59 +02:00
Falko Victor Habel	a8ddf2b559	updated config to not handle ustom model_name; removed ln rate and made it transformer compatible	2025-04-13 22:18:26 +02:00
Falko Victor Habel	ba6da9ef02	restored full example	2025-04-13 22:17:46 +02:00
Falko Victor Habel	22e5d0023e	updated pretrainer to feature PreTrainedModel	2025-04-12 21:44:53 +02:00
Falko Victor Habel	30695154b4	removed depcreated models from init files	2025-04-12 21:44:33 +02:00
Falko Victor Habel	d4db1ef116	updated tests for transfomer switch	2025-04-12 21:44:03 +02:00
Falko Victor Habel	bf915a4dca	added transformers to requirements	2025-04-11 22:40:00 +02:00
Falko Victor Habel	040ac478b9	removed loading and saving functions since tf will take over	2025-04-11 22:37:44 +02:00
Falko Victor Habel	0852ddb109	removed the chunked and recursive model, since they are now depreacted. for the transfomer switch I decided to focus on my idea with Sparse Mixutre of Experts with shared Params.	2025-04-11 22:36:41 +02:00
Falko Victor Habel	18249a852a	Merge pull request 'feat/smoe' (#34) from feat/smoe into main ... Reviewed-on: #34	2025-03-28 15:48:40 +00:00
Falko Victor Habel	fb1b25507c	added Expert to model to fix test	2025-03-28 16:10:22 +01:00
Falko Victor Habel	5987a130f6	updated init to remove expeort model and move the smoe higher	2025-03-26 21:57:17 +01:00
Falko Victor Habel	458d78a23e	removed full vectorizing	2025-03-26 21:26:30 +01:00
Falko Victor Habel	c0e36cd579	added basic tests for sparse moe	2025-03-26 21:26:14 +01:00
Falko Victor Habel	10967ea880	added sparse moe	2025-03-26 21:26:00 +01:00
Falko Victor Habel	1fcb31b044	removed aiia from being able to get called	2025-03-26 21:25:52 +01:00
Falko Victor Habel	96d8e18ee0	updated software version	2025-03-26 21:25:38 +01:00
Falko Victor Habel	2d5fcd91d5	Merge pull request 'fixed correct path for vector loading' (#33) from feat/cicd into main ... Reviewed-on: #33	2025-03-16 12:17:16 +00:00
Falko Victor Habel	153ccc9f1d	fixed correct path for vector loading	2025-03-16 13:16:52 +01:00
Falko Victor Habel	e0b3cfb20f	Merge pull request 'feat/tests' (#32) from feat/tests into main ... Reviewed-on: #32	2025-03-16 12:10:19 +00:00
Falko Victor Habel	ed4fedd403	added missing mock installation	2025-03-16 13:09:03 +01:00
Falko Victor Habel	4e6a02cdc9	updated model version	2025-03-16 13:00:07 +01:00
Falko Victor Habel	9d89c6c534	fixed double tests	2025-03-16 12:59:58 +01:00
Falko Victor Habel	217a1f85d7	Merge pull request 'added cicd tests' (#31) from cicd into develop ... Reviewed-on: #31	2025-03-16 11:26:49 +00:00
Falko Victor Habel	64787cbffc	Merge pull request 'feat/added_tests' (#30) from feat/added_tests into develop ... Reviewed-on: #30	2025-03-16 11:26:34 +00:00
Falko Victor Habel	3735bdd3e6	Merge pull request 'added tests' (#29) from added_tests into develop ... Reviewed-on: #29	2025-03-16 11:26:12 +00:00
Falko Victor Habel	633e6c8459	Merge pull request 'fixed model loading to support all models' (#28) from feat/load_fix into develop ... Reviewed-on: #28	2025-03-16 11:25:41 +00:00
Falko Victor Habel	47d3ee89a6	fixed tests	2025-03-16 12:24:26 +01:00
Falko Victor Habel	55f00b7906	added pytest files	2025-03-15 23:42:19 +01:00
Falko Victor Habel	fd518ff080	fixed Dataloader and added test cases.	2025-03-15 23:42:08 +01:00
Falko Victor Habel	24a3a7bf56	added tests for pretrainer	2025-03-15 23:12:39 +01:00
Falko Victor Habel	cd317ce0e9	added model tests	2025-03-15 18:55:55 +01:00
Falko Victor Habel	19bffa99d6	fixed model loading to support all models	2025-03-15 18:53:26 +01:00
Falko Victor Habel	da93db23c0	added tests	2025-03-15 18:48:27 +01:00
Falko Victor Habel	83fce24a6a	added cicd tests	2025-03-15 18:45:48 +01:00
Falko Victor Habel	5f16b6ca6c	Merge pull request 'develop' (#27) from develop into main ... Reviewed-on: #27	2025-03-11 21:26:42 +00:00
Falko Victor Habel	7f55ede587	Merge pull request 'corrected modelloading to also accept kwargs when e.g. using base models in Combination with expert models' (#26) from feat/bugfix_loading into develop ... Reviewed-on: #26	2025-03-11 21:26:31 +00:00
Falko Victor Habel	e5181c3066	corrected modelloading to also accept kwargs when e.g. using base models in Combination with expert models	2025-03-11 22:13:17 +01:00
Falko Victor Habel	2eee873247	Merge pull request 'gates where not saved as well' (#25) from bug_fixes into main ... Reviewed-on: #25	2025-03-03 18:02:00 +00:00
Falko Victor Habel	35edadf727	gates where not saved as well	2025-03-03 19:01:29 +01:00
Falko Victor Habel	6d8eeb2011	Merge pull request 'back to og transfomer size' (#24) from bug_fixes into main ... Reviewed-on: #24	2025-03-03 17:40:55 +00:00
Falko Victor Habel	91728a0469	back to og transfomer size	2025-03-03 18:40:22 +01:00
Falko Victor Habel	b7215bba7f	Merge pull request 'downsized transfomrers per iamge' (#23) from bug_fixes into main ... Reviewed-on: #23	2025-03-03 17:31:51 +00:00
Falko Victor Habel	e5ed04fa25	downsized transfomrers per iamge	2025-03-03 18:31:26 +01:00
Falko Victor Habel	f14ed76b42	Merge pull request 'updated version' (#22) from bug_fixes into main ... Reviewed-on: #22	2025-03-03 17:24:58 +00:00