| base_model: Qwen/Qwen2.5-7B-Instruct | |
| dtype: bfloat16 | |
| merge_method: slerp | |
| parameters: | |
| t: | |
| - filter: self_attn | |
| value: [0.0, 0.5, 0.3, 0.7, 1.0] | |
| - filter: mlp | |
| value: [1.0, 0.5, 0.7, 0.3, 0.0] | |
| - value: 0.9 | |
| slices: | |
| - sources: | |
| - layer_range: [0, 28] | |
| model: Qwen/Qwen2.5-7B-Instruct | |
| - layer_range: [0, 28] | |
| model: Qwen/Qwen2-7B-Instruct |