| base_model: Qwen/Qwen2-72B-Instruct | |
| dtype: bfloat16 | |
| merge_method: slerp | |
| 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 | |
| slices: | |
| - sources: | |
| - layer_range: | |
| - 0 | |
| - 80 | |
| model: Qwen/Qwen2-72B-Instruct | |
| - layer_range: | |
| - 0 | |
| - 80 | |
| model: cognitivecomputations/dolphin-2.9.2-qwen2-72b | |