| models: | |
| - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF | |
| - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF | |
| merge_method: slerp | |
| base_model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF | |
| dtype: float32 | |
| parameters: | |
| t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers | |