Commit Graph
20 Commits
Author SHA1 Message Date
Benjamin Greene 4b45cff13d Merge remote-tracking branch 'origin/main' into quantization 2025-10-13 11:42:16 -05:00
Ben Greene 7a9da0de7e add to readme (#22) 2025-10-13 11:41:43 -05:00
Benjamin Greene a2872fe259 update readme 2025-10-13 11:26:08 -05:00
Benjamin Greene 998dbd18c4 fix bug -> load_in_8bit and load_in_4bit were misnamed 2025-10-12 22:28:57 -05:00
Benjamin Greene f85e3c515b Merge remote-tracking branch 'origin/main' into quantization 2025-10-12 17:04:53 -05:00
Ben Greene 5a2168ff8c fix cfg slider (#20) v1.2.1 2025-10-12 17:02:00 -05:00
Benjamin Greene a91740f670 split model loading configuration into a separate node, add quantization config 2025-10-12 16:59:51 -05:00
Ben Greeneandtimkhronos a8536dd124 Release 1.2.0 (#19)
* add device map override functionality

* fix syntax

* update readme

* Edit inference file so it keeps memory reserved

* prepare release branch

* make it so that the model is optionally unloaded between generations

* remove newline

* update assets and example workflow

* update pyproject

* reload the model if settings have changed; use model if it's already … (#16)

* reload the model if settings have changed; use model if it's already loaded even if keep_model_in_memory is false

* update readme

* prepare relase 1.2.0

* Add moe drop tokens (#18)

* moe_drop_tokens option

* log kwargs, change readme

* make moe_drop_tokens the default

* edit readme

---------

Co-authored-by: timkhronos <timkhronos@gmail.com>
v1.2.0
2025-10-12 10:15:54 -05:00
Ben Greeneandtimkhronos 980a2f9334 Release 1.1.0 (#14)
* add device map override functionality

* fix syntax

* update readme

* Edit inference file so it keeps memory reserved

* prepare release branch

* make it so that the model is optionally unloaded between generations

* remove newline

* update assets and example workflow

---------

Co-authored-by: timkhronos <timkhronos@gmail.com>
2025-10-11 20:09:04 -05:00
Benjamin Greene 8a60093d46 update pyproject.toml v1.0.2 2025-10-10 09:01:53 -05:00
Ben Greene 3c2dcf611e Merge pull request #9 from bgreene2/fix_dimensions
swap width-height
2025-10-10 09:00:35 -05:00
Benjamin Greene b3161f2091 swap width-height 2025-10-10 08:58:11 -05:00
Benjamin Greene 969c913acf hotfix readme 2025-10-06 23:46:36 -05:00
Benjamin Greene 4341dbad41 update readme 2025-10-06 23:45:52 -05:00
Benjamin Greene e49c024876 add pyproject.toml 2025-10-06 23:44:46 -05:00
Benjamin Greene e286e12764 edit footnotes in readme 2025-10-06 23:39:41 -05:00
Benjamin Greene 891afde515 fix bug in image output, fix bug where parameters were not being passed 2025-10-06 23:38:12 -05:00
Benjamin Greene 0b37115d5a add information on setting the correct Pytorch CUDA backend to the README 2025-10-06 20:51:54 -05:00
Benjamin Greene 511f7898dd initial commit 2025-10-06 17:12:52 -05:00
Ben Greene 036f7309b6 Initial commit 2025-10-06 16:50:21 -05:00