models: | |
- model: "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B" | |
parameters: | |
weight: 1 | |
density: 1 | |
merge_method: ties | |
base_model: "Qwen/Qwen2.5-Coder-1.5B-Instruct" | |
parameters: | |
density: 1 | |
normalize: true | |
int8_mask: true | |
dtype: bfloat16 | |
models: | |
- model: "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B" | |
parameters: | |
weight: 1 | |
density: 1 | |
merge_method: ties | |
base_model: "Qwen/Qwen2.5-Coder-1.5B-Instruct" | |
parameters: | |
density: 1 | |
normalize: true | |
int8_mask: true | |
dtype: bfloat16 | |