| base_model: NousResearch/Meta-Llama-3-8B-Instruct | |
| dtype: float32 | |
| merge_method: task_arithmetic | |
| parameters: | |
| normalize: 0.0 | |
| slices: | |
| - sources: | |
| - layer_range: [0, 32] | |
| model: output/hq_rp | |
| parameters: | |
| weight: | |
| - filter: mlp | |
| value: 1.15 | |
| - filter: self_attn | |
| value: 1.025 | |
| - value: 1.0 | |
| - layer_range: [0, 32] | |
| model: NousResearch/Meta-Llama-3-8B-Instruct |