“Style strength” knob via LoRA scaling
#41
by
jbakerx
- opened
Expose a parameter like style_strength by scaling the adapter weights at inference:
0.0 = base model
0.5 = subtle classical tone
1.0 = full Tolstoy register
This is easy, user-friendly, and demo-ready.
We will consider this enhancement for inclusion in version 2.0.0.