Commit Graph

153 Commits

Author SHA1 Message Date
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
Falko Victor Habel 6221a90a56 updated version 2025-03-03 18:24:32 +01:00
Falko Victor Habel 3b018a6761 Merge pull request 'to 384 from 400' (#21) from bug_fixes into main
Reviewed-on: #21
2025-03-03 17:12:06 +00:00
Falko Victor Habel 1354817304 to 384 from 400 2025-03-03 18:11:29 +01:00
Falko Victor Habel d41ec2d82a Merge pull request 'saving 100px in pretraining' (#20) from bug_fixes into main
Reviewed-on: #20
2025-03-03 17:07:31 +00:00
Falko Victor Habel 5347c1b17a saving 100px in pretraining 2025-03-03 18:06:42 +01:00
Falko Victor Habel 8703835ea7 Merge pull request 'correctly init moe class' (#19) from bug_fixes into main
Reviewed-on: #19
2025-03-03 16:46:04 +00:00
Falko Victor Habel cf41d0f6f6 correctly init moe class 2025-03-03 17:45:36 +01:00
Falko Victor Habel 4f57905ed8 Merge pull request 'updated model for moe' (#18) from bug_fixes into main
Reviewed-on: #18
2025-03-03 16:39:42 +00:00
Falko Victor Habel 81c9ae9d9d updated model for moe 2025-03-03 17:39:04 +01:00
Falko Victor Habel 89d9efb41f Merge pull request 'fixed model output' (#17) from bug_fixes into main
Reviewed-on: #17
2025-03-03 16:06:57 +00:00
Falko Victor Habel 899f714554 fixed model output 2025-03-03 17:05:35 +01:00
Falko Victor Habel 4e7d0d806f Merge pull request 'bug fixing realted to storing losses' (#16) from bug_fixes into main
Reviewed-on: #16
2025-03-03 12:33:49 +00:00
Falko Victor Habel c06217db1e bug fixing realted to storing losses 2025-03-02 14:48:43 +01:00
Falko Victor Habel 40c2b6dd50 Merge pull request 'develop' (#15) from develop into main
Reviewed-on: #15
2025-03-02 13:28:05 +00:00
Falko Victor Habel ee58b085f5 Merge pull request 'bugfix' (#14) from feat/fix_saving into develop
Reviewed-on: #14
2025-03-02 13:27:51 +00:00
Falko Victor Habel 66762775e9 bugfix 2025-03-02 14:27:26 +01:00
Falko Victor Habel 8d05481498 Merge pull request 'feat/fix_saving' (#13) from feat/fix_saving into main
Reviewed-on: #13
2025-03-01 21:54:36 +00:00
Falko Victor Habel 06a2e012e8 fixed project files 2025-02-27 22:00:48 +01:00
Falko Victor Habel cb7a23f3ae fixed licence 2025-02-27 21:57:39 +01:00
Falko Victor Habel e74be9cbc3 fixed setup with correct naming 2025-02-27 21:56:50 +01:00
Falko Victor Habel 5205a73811 Merge pull request 'develop' (#12) from develop into main
Reviewed-on: #12
2025-02-27 17:57:28 +00:00
Falko Victor Habel 8cf26dc72f Merge pull request 'updated version to support proper saving when pretraining' (#11) from feat/fix_saving into develop
Reviewed-on: #11
2025-02-27 17:57:17 +00:00
Falko Victor Habel 3cb2a18ad9 updated version to support proper saving when pretraining 2025-02-27 18:56:42 +01:00
Falko Victor Habel ad0bcaee17 Merge pull request 'added serilatsation' (#10) from half_precision into main
Reviewed-on: #10
2025-02-24 14:17:15 +00:00
Falko Victor Habel 1faf34749a added serilatsation 2025-02-24 15:16:46 +01:00
Falko Victor Habel f7fa8c0a50 Merge pull request 'develop' (#9) from develop into main
Reviewed-on: #9
2025-02-24 13:17:54 +00:00
Falko Victor Habel 3859270cc4 Merge pull request 'updated readme' (#8) from half_precision into develop
Reviewed-on: #8
2025-02-24 13:17:44 +00:00
Falko Victor Habel c9b6a8926b updated readme 2025-02-24 14:17:25 +01:00
Falko Victor Habel 91f352340d Merge pull request 'half_precision' (#7) from half_precision into develop
Reviewed-on: #7
2025-02-24 13:14:00 +00:00
Falko Victor Habel 027676d95e Merge pull request 'added cpu support when loading the model' (#6) from cpu_support into develop
Reviewed-on: #6
2025-02-24 13:13:45 +00:00
Falko Victor Habel 50e91b10e8 fixed model loading due to a bug 2025-02-24 14:13:10 +01:00
Falko Victor Habel b1c486afee added fp16 and bf16 support when loading model 2025-02-24 13:41:11 +01:00
Falko Victor Habel f8e59c5896 added cpu support when loading the model 2025-01-31 09:13:58 +01:00
Falko Victor Habel a2909002a7 Merge pull request 'develop' (#5) from develop into main
Reviewed-on: Fabel/AIIA#5
2025-01-29 21:33:57 +00:00
Falko Victor Habel 0d5e5688eb Merge pull request 'first_pip' (#4) from first_pip into develop
Reviewed-on: Fabel/AIIA#4
2025-01-29 21:33:31 +00:00
Falko Victor Habel 3c0e9e8ac1 fixed savings 2025-01-28 17:18:21 +01:00
Falko Victor Habel 3631df7f0a updated pretrainer to handle multiple classes and configs. 2025-01-28 11:42:03 +01:00
Falko Victor Habel a369c49f15 improved pretraining 2025-01-28 11:27:42 +01:00
Falko Victor Habel 1e79a93a5e Merge pull request 'improved_shared_cnn' (#3) from improved_shared_cnn into develop
Reviewed-on: Fabel/AIIA#3
2025-01-28 10:18:45 +00:00
Falko Victor Habel 7de7eef081 updated pretraing to create a extra class for Pretraining 2025-01-28 11:16:09 +01:00
Falko Victor Habel 1e665c4604 added first pip install version 0.1 2025-01-28 10:58:33 +01:00