models: | |
- model: RLHFlow/LLaMA3-iterative-DPO-final | |
- model: bunnycore/Maverick-8B | |
- model: TIGER-Lab/MAmmoTH2-8B-Plus | |
merge_method: model_stock | |
base_model: bunnycore/Maverick-8B | |
dtype: bfloat16 | |
models: | |
- model: RLHFlow/LLaMA3-iterative-DPO-final | |
- model: bunnycore/Maverick-8B | |
- model: TIGER-Lab/MAmmoTH2-8B-Plus | |
merge_method: model_stock | |
base_model: bunnycore/Maverick-8B | |
dtype: bfloat16 | |