AI-Casanova 9c7237157d Dropout and Max Norm Regularization for LoRA training (#545) ...

* Instantiate max_norm

* minor

* Move to end of step

* argparse

* metadata

* phrasing

* Sqrt ratio and logging

* fix logging

* Dropout test

* Dropout Args

* Dropout changed to affect LoRA only

---------

Co-authored-by: Kohya S <52813779+kohya-ss@users.noreply.github.com>

2023-06-01 14:58:38 +09:00

..

check_lora_weights.py

Extract parser setup to helper function

2023-03-20 00:06:47 -04:00

dylora.py

fix load_state_dict failed in dylora

2023-04-14 22:13:26 +09:00

extract_lora_from_dylora.py

remove unnecessary newline

2023-05-11 21:20:18 +09:00

extract_lora_from_models.py

Add block dim(rank) feature

2023-04-03 21:19:49 +09:00

lora_interrogator.py

Fix DDP issues and Support DDP for all training scripts (#448)

2023-05-03 10:37:47 +09:00

lora.py

Dropout and Max Norm Regularization for LoRA training (#545)

2023-06-01 14:58:38 +09:00

merge_lora_old.py

fix print "saving" and "epoch" in newline

2023-05-07 02:51:01 +08:00

merge_lora.py

remove unnecessary newline

2023-05-11 21:20:18 +09:00

resize_lora.py

remove unnecessary newline

2023-05-11 21:20:18 +09:00

svd_merge_lora.py

remove unnecessary newline

2023-05-11 21:20:18 +09:00