| models: | |
| - model: ArliAI/Gemma-2-9B-ArliAI-RPMax-v1.1 | |
| - model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3 | |
| merge_method: slerp | |
| base_model: ArliAI/Gemma-2-9B-ArliAI-RPMax-v1.1 | |
| dtype: bfloat16 | |
| parameters: | |
| t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers | |