| models: | |
| - model: nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct | |
| - model: mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1 | |
| merge_method: slerp | |
| base_model: nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct | |
| dtype: bfloat16 | |
| parameters: | |
| t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers | |