Usage
# ===== Before =====
# layer = nn.Linear(in_features, out_features)
# ===== After ======
layer = male.MLAE_Linear(in_features, out_features, r=rank, lora_alpha=lora_alpha, drop_rate=drop_rate)-
Notifications
You must be signed in to change notification settings - Fork 2
jie040109/MLAE
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
The official PyTorch implementation of the paper "MLAE: Masked LoRA Experts for Visual Parameter-Efficient Fine-Tuning"