Merging this lora into klein-9b pushes it toward the klein-base-9b's non-distilled behavior, allowing finetuning on distilled klein-9b without degradation.
How this lora was made:
Computed delta = klein-base-9b - klein-9b distilled
Run SVD on that delta and keep only top rank 128 components.
Created using musubi-tuner.
Have the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo kenzato/flux2-klein-9b_deturbo_train_adapter_r128 ./model-folder