| merge_method: slerp | |
| base_model: Qwen/QwQ-32B | |
| tokenizer_source: Qwen/QwQ-32B | |
| dtype: bfloat16 | |
| out_dtype: bfloat16 | |
| parameters: | |
| int8_mask: true | |
| normalize: true | |
| rescale: false | |
| t: | |
| - value: 0.50 | |
| slices: | |
| - sources: | |
| - model: Qwen/QwQ-32B | |
| layer_range: [ 0, 8 ] | |
| - model: Qwen/QwQ-32B | |
| layer_range: [ 0, 8 ] | |
| - sources: | |
| - model: Qwen/Qwen2.5-32B-Instruct | |
| layer_range: [ 8, 16 ] | |
| - model: Qwen/QwQ-32B | |
| layer_range: [ 8, 16 ] | |
| - sources: | |
| - model: Qwen/Qwen2.5-32B-Instruct | |
| layer_range: [ 16, 24 ] | |
| - model: Qwen/QwQ-32B | |
| layer_range: [ 16, 24 ] | |
| - sources: | |
| - model: Qwen/Qwen2.5-32B-Instruct | |
| layer_range: [ 24, 32 ] | |
| - model: Qwen/Qwen2.5-32B-Instruct | |
| layer_range: [ 24, 32 ] | |
| - sources: | |
| - model: Qwen/Qwen2.5-32B-Instruct | |
| layer_range: [ 32, 40 ] | |
| - model: Qwen/Qwen2.5-32B-Instruct | |
| layer_range: [ 32, 40 ] | |
| - sources: | |
| - model: Qwen/QwQ-32B | |
| layer_range: [ 40, 48 ] | |
| - model: Qwen/Qwen2.5-32B-Instruct | |
| layer_range: [ 40, 48 ] | |
| - sources: | |
| - model: Qwen/QwQ-32B | |
| layer_range: [ 48, 56 ] | |
| - model: Qwen/Qwen2.5-32B-Instruct | |
| layer_range: [ 48, 56 ] | |
| - sources: | |
| - model: Qwen/QwQ-32B | |
| layer_range: [ 56, 64 ] | |
| - model: Qwen/QwQ-32B | |
| layer_range: [ 56, 64 ] | |