| models: | |
| - model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B | |
| parameters: | |
| weight: 1 | |
| density: 1 | |
| - model: nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct | |
| parameters: | |
| weight: 1 | |
| density: 1 | |
| merge_method: ties | |
| base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B | |
| parameters: | |
| density: 1 | |
| normalize: true | |
| int8_mask: true | |
| dtype: bfloat16 | |