Model description
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.