models: | |
- model: bunnycore/FuseChat-3.2-1B-Creative-RP | |
- model: NickyNicky/Llama-1B-GRPO_Final | |
merge_method: slerp | |
base_model: bunnycore/FuseChat-3.2-1B-Creative-RP | |
dtype: bfloat16 | |
parameters: | |
t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers | |