| slices: | |
| - sources: | |
| - model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 | |
| layer_range: [0, 32] | |
| - model: NousResearch/Hermes-2-Theta-Llama-3-8B | |
| layer_range: [0, 32] | |
| merge_method: slerp | |
| base_model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 | |
| parameters: | |
| t: | |
| - filter: self_attn | |
| value: [0, 0.5, 0.3, 0.7, 1] | |
| - filter: mlp | |
| value: [1, 0.5, 0.7, 0.3, 0] | |
| - value: 0.5 | |
| dtype: bfloat16 |