| base_model: Qwen/Qwen2.5-7B-Instruct | |
| dtype: bfloat16 | |
| merge_method: ties | |
| parameters: | |
| int8_mask: 1.0 | |
| normalize: 1.0 | |
| slices: | |
| - sources: | |
| - layer_range: [0, 28] | |
| model: Qwen/Qwen2.5-7B-Instruct | |
| parameters: | |
| density: 0.7 | |
| weight: 0.4 | |
| - layer_range: [0, 28] | |
| model: DHMATH/Qwen-7B-Instruct | |
| parameters: | |
| density: 1.0 | |
| weight: 0.6 | |
| tokenizer_source: DHMATH/Qwen-7B-Instruct |