slices: | |
- sources: | |
- model: mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1 | |
layer_range: [0, 28] | |
- model: MasterControlAIML/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured | |
layer_range: [0, 28] | |
merge_method: slerp | |
base_model: mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1 | |
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 | |
dtype: bfloat16 |