| models: | |
| - model: Qwen/Qwen2.5-Coder-7B-Instruct | |
| - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B | |
| parameters: | |
| density: 0.2 | |
| weight: 0.1 | |
| merge_method: dare_ties | |
| base_model: Qwen/Qwen2.5-Coder-7B-Instruct | |
| dtype: bfloat16 | |
| tokenizer_source: "base" |
| models: | |
| - model: Qwen/Qwen2.5-Coder-7B-Instruct | |
| - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B | |
| parameters: | |
| density: 0.2 | |
| weight: 0.1 | |
| merge_method: dare_ties | |
| base_model: Qwen/Qwen2.5-Coder-7B-Instruct | |
| dtype: bfloat16 | |
| tokenizer_source: "base" |