models: | |
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B | |
# no parameters necessary for base model | |
- model: Qwen/Qwen2.5-Coder-1.5B-Instruct | |
parameters: | |
density: 0.5 | |
weight: 0.5 | |
- model: Qwen/Qwen2.5-Math-1.5B-Instruct | |
parameters: | |
density: 0.6 | |
weight: 0.5 | |
- model: Qwen/Qwen2.5-1.5B | |
parameters: | |
density: 0.6 | |
weight: 0.5 | |
- model: agentica-org/DeepScaleR-1.5B-Preview | |
parameters: | |
density: 0.4 | |
weight: 0.6 | |
merge_method: ties | |
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B | |
parameters: | |
normalize: true | |
dtype: float16 | |