| models: | |
| - model: NousResearch/Hermes-2-Theta-Llama-3-8B | |
| parameters: | |
| weight: 0.6 | |
| - model: MaziyarPanahi/Llama-3-8B-Instruct-v0.8 | |
| parameters: | |
| weight: 0.4 | |
| merge_method: task_arithmetic | |
| base_model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 | |
| dtype: bfloat16 |
| models: | |
| - model: NousResearch/Hermes-2-Theta-Llama-3-8B | |
| parameters: | |
| weight: 0.6 | |
| - model: MaziyarPanahi/Llama-3-8B-Instruct-v0.8 | |
| parameters: | |
| weight: 0.4 | |
| merge_method: task_arithmetic | |
| base_model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 | |
| dtype: bfloat16 |