YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Some LoRAs pruned using resize_lora.py in Kohya's sd-scripts. Their sizes are greatly reduced to help save VRAM.
Pruning also acts as a regularization to prevent the LoRA from overfitting to what has been trained.
Pruning also roughly shows how much information the LoRA has learned. For two LoRAs with the same rank and fro, the larger one has more information.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support