mgz-dev 4a4450d6b6 make new_rank limit max rank, fix zero matrices ...

-new_rank arg changed to limit the max rank of any layer.
-added logic to make sure zero-ed layers do not create large lora dim

2023-03-04 03:10:04 -06:00

..

check_lora_weights.py

Fix weights checking script to use float32

2023-01-22 10:44:29 +09:00

extract_lora_from_models.py

Update for alpha value

2023-01-22 21:33:35 +09:00

lora_interrogator.py

add message

2023-02-11 13:20:58 +09:00

lora.py

support network mul from prompt

2023-02-19 18:43:35 +09:00

merge_lora_old.py

support for models with different alphas

2023-02-10 22:54:35 +09:00

merge_lora.py

support for models with different alphas

2023-02-10 22:54:35 +09:00

resize_lora.py

make new_rank limit max rank, fix zero matrices

2023-03-04 03:10:04 -06:00

svd_merge_lora.py

add merge script with svd

2023-02-10 22:55:33 +09:00