models: | |
- model: Lyra-DPO-18B | |
parameters: | |
weight: 0.2 | |
density: 0.5 | |
- model: Instruct-DPO-18B | |
parameters: | |
weight: 0.3 | |
density: 0.6 | |
- model: Magnum-DPO-18B | |
parameters: | |
weight: 0.5 | |
density: 0.8 | |
merge_method: della_linear | |
base_model: Instruct-DPO-18B | |
parameters: | |
epsilon: 0.04 | |
lambda: 1.05 | |
dtype: bfloat16 | |
tokenzer_source: union | |