For each component 7b, do

Stack A: [0, 28], [12, 32]
Stack B: [0, 20], [4, 32]
Linear merge: 
	Stack A weight [1, 1, 1, 1, 1, 0.5, 0, 0, 0, 0, 0]
	Stack B weight [0, 0, 0, 0, 0, 0.5, 1, 1, 1, 1, 1]

Final merge:
- Toppy stack
- Buttocks stack
- Westlake stack
merge_method: model_stock
base_model: Mistral stack